Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache License 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Tao Zhong
- Shunsuke Miura
Authors
traffic_light_fine_detector
Purpose
It is a package for traffic light detection using YoloX-s.
Training Information
Pretrained Model
The model is based on YOLOX and the pretrained model could be downloaded from here.
Training Data
The model was fine-tuned on around 17,000 TIER IV internal images of Japanese traffic lights.
Trained Onnx model
You can download the ONNX file using these instructions. Please visit autoware-documentation for more information.
Inner-workings / Algorithms
Based on the camera image and the global ROI array detected by map_based_detection node, a CNN-based detection method enables highly accurate traffic light detection.
Inputs / Outputs
Input
| Name | Type | Description |
|---|---|---|
~/input/image |
sensor_msgs/Image |
The full size camera image |
~/input/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector |
~/expect/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector without any offset |
Output
| Name | Type | Description |
|---|---|---|
~/output/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The detected accurate rois |
~/debug/exe_time_ms |
tier4_debug_msgs::msg::Float32Stamped |
The time taken for inference |
Parameters
Core Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
fine_detector_score_thresh |
double | 0.3 | If the objectness score is less than this value, the object is ignored |
fine_detector_nms_thresh |
double | 0.65 | IoU threshold to perform Non-Maximum Suppression |
Node Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
data_path |
string | ”$(env HOME)/autoware_data” | packages data and artifacts directory path |
fine_detector_model_path |
string | ”” | The onnx file name for yolo model |
fine_detector_label_path |
string | ”” | The label file with label names for detected objects written on it |
fine_detector_precision |
string | “fp32” | The inference mode: “fp32”, “fp16” |
approximate_sync |
bool | false | Flag for whether to ues approximate sync policy |
Assumptions / Known limits
Reference repositories
YOLOX github repository
Package Dependencies
| Deps | Name |
|---|---|
| autoware_cmake | |
| ament_cmake_auto | |
| autoware_lint_common | |
| cv_bridge | |
| image_transport | |
| message_filters | |
| rclcpp | |
| rclcpp_components | |
| sensor_msgs | |
| tensorrt_yolox | |
| tier4_debug_msgs | |
| tier4_perception_msgs |
System Dependencies
Dependant Packages
| Name | Deps |
|---|---|
| tier4_perception_launch |
Launch files
- launch/traffic_light_fine_detector.launch.xml
-
- data_path [default: $(env HOME)/autoware_data]
- fine_detector_label_path [default: $(var data_path)/traffic_light_fine_detector/tlr_labels.txt]
- fine_detector_model_path [default: $(var data_path)/traffic_light_fine_detector/tlr_yolox_s_batch_6.onnx]
- fine_detector_precision [default: fp16]
- fine_detector_score_thresh [default: 0.3]
- fine_detector_nms_thresh [default: 0.65]
- input/image [default: /image_raw]
- input/rois [default: /traffic_light_map_based_detector/output/rois]
- expect/rois [default: ~/expect/rois]
- output/rois [default: ~/output/rois]
- build_only [default: false]
Messages
Services
Plugins
Recent questions tagged traffic_light_fine_detector at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache License 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Tao Zhong
- Shunsuke Miura
Authors
traffic_light_fine_detector
Purpose
It is a package for traffic light detection using YoloX-s.
Training Information
Pretrained Model
The model is based on YOLOX and the pretrained model could be downloaded from here.
Training Data
The model was fine-tuned on around 17,000 TIER IV internal images of Japanese traffic lights.
Trained Onnx model
You can download the ONNX file using these instructions. Please visit autoware-documentation for more information.
Inner-workings / Algorithms
Based on the camera image and the global ROI array detected by map_based_detection node, a CNN-based detection method enables highly accurate traffic light detection.
Inputs / Outputs
Input
| Name | Type | Description |
|---|---|---|
~/input/image |
sensor_msgs/Image |
The full size camera image |
~/input/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector |
~/expect/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector without any offset |
Output
| Name | Type | Description |
|---|---|---|
~/output/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The detected accurate rois |
~/debug/exe_time_ms |
tier4_debug_msgs::msg::Float32Stamped |
The time taken for inference |
Parameters
Core Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
fine_detector_score_thresh |
double | 0.3 | If the objectness score is less than this value, the object is ignored |
fine_detector_nms_thresh |
double | 0.65 | IoU threshold to perform Non-Maximum Suppression |
Node Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
data_path |
string | ”$(env HOME)/autoware_data” | packages data and artifacts directory path |
fine_detector_model_path |
string | ”” | The onnx file name for yolo model |
fine_detector_label_path |
string | ”” | The label file with label names for detected objects written on it |
fine_detector_precision |
string | “fp32” | The inference mode: “fp32”, “fp16” |
approximate_sync |
bool | false | Flag for whether to ues approximate sync policy |
Assumptions / Known limits
Reference repositories
YOLOX github repository
Package Dependencies
| Deps | Name |
|---|---|
| autoware_cmake | |
| ament_cmake_auto | |
| autoware_lint_common | |
| cv_bridge | |
| image_transport | |
| message_filters | |
| rclcpp | |
| rclcpp_components | |
| sensor_msgs | |
| tensorrt_yolox | |
| tier4_debug_msgs | |
| tier4_perception_msgs |
System Dependencies
Dependant Packages
| Name | Deps |
|---|---|
| tier4_perception_launch |
Launch files
- launch/traffic_light_fine_detector.launch.xml
-
- data_path [default: $(env HOME)/autoware_data]
- fine_detector_label_path [default: $(var data_path)/traffic_light_fine_detector/tlr_labels.txt]
- fine_detector_model_path [default: $(var data_path)/traffic_light_fine_detector/tlr_yolox_s_batch_6.onnx]
- fine_detector_precision [default: fp16]
- fine_detector_score_thresh [default: 0.3]
- fine_detector_nms_thresh [default: 0.65]
- input/image [default: /image_raw]
- input/rois [default: /traffic_light_map_based_detector/output/rois]
- expect/rois [default: ~/expect/rois]
- output/rois [default: ~/output/rois]
- build_only [default: false]
Messages
Services
Plugins
Recent questions tagged traffic_light_fine_detector at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache License 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Tao Zhong
- Shunsuke Miura
Authors
traffic_light_fine_detector
Purpose
It is a package for traffic light detection using YoloX-s.
Training Information
Pretrained Model
The model is based on YOLOX and the pretrained model could be downloaded from here.
Training Data
The model was fine-tuned on around 17,000 TIER IV internal images of Japanese traffic lights.
Trained Onnx model
You can download the ONNX file using these instructions. Please visit autoware-documentation for more information.
Inner-workings / Algorithms
Based on the camera image and the global ROI array detected by map_based_detection node, a CNN-based detection method enables highly accurate traffic light detection.
Inputs / Outputs
Input
| Name | Type | Description |
|---|---|---|
~/input/image |
sensor_msgs/Image |
The full size camera image |
~/input/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector |
~/expect/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector without any offset |
Output
| Name | Type | Description |
|---|---|---|
~/output/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The detected accurate rois |
~/debug/exe_time_ms |
tier4_debug_msgs::msg::Float32Stamped |
The time taken for inference |
Parameters
Core Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
fine_detector_score_thresh |
double | 0.3 | If the objectness score is less than this value, the object is ignored |
fine_detector_nms_thresh |
double | 0.65 | IoU threshold to perform Non-Maximum Suppression |
Node Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
data_path |
string | ”$(env HOME)/autoware_data” | packages data and artifacts directory path |
fine_detector_model_path |
string | ”” | The onnx file name for yolo model |
fine_detector_label_path |
string | ”” | The label file with label names for detected objects written on it |
fine_detector_precision |
string | “fp32” | The inference mode: “fp32”, “fp16” |
approximate_sync |
bool | false | Flag for whether to ues approximate sync policy |
Assumptions / Known limits
Reference repositories
YOLOX github repository
Package Dependencies
| Deps | Name |
|---|---|
| autoware_cmake | |
| ament_cmake_auto | |
| autoware_lint_common | |
| cv_bridge | |
| image_transport | |
| message_filters | |
| rclcpp | |
| rclcpp_components | |
| sensor_msgs | |
| tensorrt_yolox | |
| tier4_debug_msgs | |
| tier4_perception_msgs |
System Dependencies
Dependant Packages
| Name | Deps |
|---|---|
| tier4_perception_launch |
Launch files
- launch/traffic_light_fine_detector.launch.xml
-
- data_path [default: $(env HOME)/autoware_data]
- fine_detector_label_path [default: $(var data_path)/traffic_light_fine_detector/tlr_labels.txt]
- fine_detector_model_path [default: $(var data_path)/traffic_light_fine_detector/tlr_yolox_s_batch_6.onnx]
- fine_detector_precision [default: fp16]
- fine_detector_score_thresh [default: 0.3]
- fine_detector_nms_thresh [default: 0.65]
- input/image [default: /image_raw]
- input/rois [default: /traffic_light_map_based_detector/output/rois]
- expect/rois [default: ~/expect/rois]
- output/rois [default: ~/output/rois]
- build_only [default: false]
Messages
Services
Plugins
Recent questions tagged traffic_light_fine_detector at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache License 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Tao Zhong
- Shunsuke Miura
Authors
traffic_light_fine_detector
Purpose
It is a package for traffic light detection using YoloX-s.
Training Information
Pretrained Model
The model is based on YOLOX and the pretrained model could be downloaded from here.
Training Data
The model was fine-tuned on around 17,000 TIER IV internal images of Japanese traffic lights.
Trained Onnx model
You can download the ONNX file using these instructions. Please visit autoware-documentation for more information.
Inner-workings / Algorithms
Based on the camera image and the global ROI array detected by map_based_detection node, a CNN-based detection method enables highly accurate traffic light detection.
Inputs / Outputs
Input
| Name | Type | Description |
|---|---|---|
~/input/image |
sensor_msgs/Image |
The full size camera image |
~/input/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector |
~/expect/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector without any offset |
Output
| Name | Type | Description |
|---|---|---|
~/output/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The detected accurate rois |
~/debug/exe_time_ms |
tier4_debug_msgs::msg::Float32Stamped |
The time taken for inference |
Parameters
Core Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
fine_detector_score_thresh |
double | 0.3 | If the objectness score is less than this value, the object is ignored |
fine_detector_nms_thresh |
double | 0.65 | IoU threshold to perform Non-Maximum Suppression |
Node Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
data_path |
string | ”$(env HOME)/autoware_data” | packages data and artifacts directory path |
fine_detector_model_path |
string | ”” | The onnx file name for yolo model |
fine_detector_label_path |
string | ”” | The label file with label names for detected objects written on it |
fine_detector_precision |
string | “fp32” | The inference mode: “fp32”, “fp16” |
approximate_sync |
bool | false | Flag for whether to ues approximate sync policy |
Assumptions / Known limits
Reference repositories
YOLOX github repository
Package Dependencies
| Deps | Name |
|---|---|
| autoware_cmake | |
| ament_cmake_auto | |
| autoware_lint_common | |
| cv_bridge | |
| image_transport | |
| message_filters | |
| rclcpp | |
| rclcpp_components | |
| sensor_msgs | |
| tensorrt_yolox | |
| tier4_debug_msgs | |
| tier4_perception_msgs |
System Dependencies
Dependant Packages
| Name | Deps |
|---|---|
| tier4_perception_launch |
Launch files
- launch/traffic_light_fine_detector.launch.xml
-
- data_path [default: $(env HOME)/autoware_data]
- fine_detector_label_path [default: $(var data_path)/traffic_light_fine_detector/tlr_labels.txt]
- fine_detector_model_path [default: $(var data_path)/traffic_light_fine_detector/tlr_yolox_s_batch_6.onnx]
- fine_detector_precision [default: fp16]
- fine_detector_score_thresh [default: 0.3]
- fine_detector_nms_thresh [default: 0.65]
- input/image [default: /image_raw]
- input/rois [default: /traffic_light_map_based_detector/output/rois]
- expect/rois [default: ~/expect/rois]
- output/rois [default: ~/output/rois]
- build_only [default: false]
Messages
Services
Plugins
Recent questions tagged traffic_light_fine_detector at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache License 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Tao Zhong
- Shunsuke Miura
Authors
traffic_light_fine_detector
Purpose
It is a package for traffic light detection using YoloX-s.
Training Information
Pretrained Model
The model is based on YOLOX and the pretrained model could be downloaded from here.
Training Data
The model was fine-tuned on around 17,000 TIER IV internal images of Japanese traffic lights.
Trained Onnx model
You can download the ONNX file using these instructions. Please visit autoware-documentation for more information.
Inner-workings / Algorithms
Based on the camera image and the global ROI array detected by map_based_detection node, a CNN-based detection method enables highly accurate traffic light detection.
Inputs / Outputs
Input
| Name | Type | Description |
|---|---|---|
~/input/image |
sensor_msgs/Image |
The full size camera image |
~/input/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector |
~/expect/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector without any offset |
Output
| Name | Type | Description |
|---|---|---|
~/output/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The detected accurate rois |
~/debug/exe_time_ms |
tier4_debug_msgs::msg::Float32Stamped |
The time taken for inference |
Parameters
Core Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
fine_detector_score_thresh |
double | 0.3 | If the objectness score is less than this value, the object is ignored |
fine_detector_nms_thresh |
double | 0.65 | IoU threshold to perform Non-Maximum Suppression |
Node Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
data_path |
string | ”$(env HOME)/autoware_data” | packages data and artifacts directory path |
fine_detector_model_path |
string | ”” | The onnx file name for yolo model |
fine_detector_label_path |
string | ”” | The label file with label names for detected objects written on it |
fine_detector_precision |
string | “fp32” | The inference mode: “fp32”, “fp16” |
approximate_sync |
bool | false | Flag for whether to ues approximate sync policy |
Assumptions / Known limits
Reference repositories
YOLOX github repository
Package Dependencies
| Deps | Name |
|---|---|
| autoware_cmake | |
| ament_cmake_auto | |
| autoware_lint_common | |
| cv_bridge | |
| image_transport | |
| message_filters | |
| rclcpp | |
| rclcpp_components | |
| sensor_msgs | |
| tensorrt_yolox | |
| tier4_debug_msgs | |
| tier4_perception_msgs |
System Dependencies
Dependant Packages
| Name | Deps |
|---|---|
| tier4_perception_launch |
Launch files
- launch/traffic_light_fine_detector.launch.xml
-
- data_path [default: $(env HOME)/autoware_data]
- fine_detector_label_path [default: $(var data_path)/traffic_light_fine_detector/tlr_labels.txt]
- fine_detector_model_path [default: $(var data_path)/traffic_light_fine_detector/tlr_yolox_s_batch_6.onnx]
- fine_detector_precision [default: fp16]
- fine_detector_score_thresh [default: 0.3]
- fine_detector_nms_thresh [default: 0.65]
- input/image [default: /image_raw]
- input/rois [default: /traffic_light_map_based_detector/output/rois]
- expect/rois [default: ~/expect/rois]
- output/rois [default: ~/output/rois]
- build_only [default: false]
Messages
Services
Plugins
Recent questions tagged traffic_light_fine_detector at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache License 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Tao Zhong
- Shunsuke Miura
Authors
traffic_light_fine_detector
Purpose
It is a package for traffic light detection using YoloX-s.
Training Information
Pretrained Model
The model is based on YOLOX and the pretrained model could be downloaded from here.
Training Data
The model was fine-tuned on around 17,000 TIER IV internal images of Japanese traffic lights.
Trained Onnx model
You can download the ONNX file using these instructions. Please visit autoware-documentation for more information.
Inner-workings / Algorithms
Based on the camera image and the global ROI array detected by map_based_detection node, a CNN-based detection method enables highly accurate traffic light detection.
Inputs / Outputs
Input
| Name | Type | Description |
|---|---|---|
~/input/image |
sensor_msgs/Image |
The full size camera image |
~/input/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector |
~/expect/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector without any offset |
Output
| Name | Type | Description |
|---|---|---|
~/output/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The detected accurate rois |
~/debug/exe_time_ms |
tier4_debug_msgs::msg::Float32Stamped |
The time taken for inference |
Parameters
Core Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
fine_detector_score_thresh |
double | 0.3 | If the objectness score is less than this value, the object is ignored |
fine_detector_nms_thresh |
double | 0.65 | IoU threshold to perform Non-Maximum Suppression |
Node Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
data_path |
string | ”$(env HOME)/autoware_data” | packages data and artifacts directory path |
fine_detector_model_path |
string | ”” | The onnx file name for yolo model |
fine_detector_label_path |
string | ”” | The label file with label names for detected objects written on it |
fine_detector_precision |
string | “fp32” | The inference mode: “fp32”, “fp16” |
approximate_sync |
bool | false | Flag for whether to ues approximate sync policy |
Assumptions / Known limits
Reference repositories
YOLOX github repository
Package Dependencies
| Deps | Name |
|---|---|
| autoware_cmake | |
| ament_cmake_auto | |
| autoware_lint_common | |
| cv_bridge | |
| image_transport | |
| message_filters | |
| rclcpp | |
| rclcpp_components | |
| sensor_msgs | |
| tensorrt_yolox | |
| tier4_debug_msgs | |
| tier4_perception_msgs |
System Dependencies
Dependant Packages
| Name | Deps |
|---|---|
| tier4_perception_launch |
Launch files
- launch/traffic_light_fine_detector.launch.xml
-
- data_path [default: $(env HOME)/autoware_data]
- fine_detector_label_path [default: $(var data_path)/traffic_light_fine_detector/tlr_labels.txt]
- fine_detector_model_path [default: $(var data_path)/traffic_light_fine_detector/tlr_yolox_s_batch_6.onnx]
- fine_detector_precision [default: fp16]
- fine_detector_score_thresh [default: 0.3]
- fine_detector_nms_thresh [default: 0.65]
- input/image [default: /image_raw]
- input/rois [default: /traffic_light_map_based_detector/output/rois]
- expect/rois [default: ~/expect/rois]
- output/rois [default: ~/output/rois]
- build_only [default: false]
Messages
Services
Plugins
Recent questions tagged traffic_light_fine_detector at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache License 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Tao Zhong
- Shunsuke Miura
Authors
traffic_light_fine_detector
Purpose
It is a package for traffic light detection using YoloX-s.
Training Information
Pretrained Model
The model is based on YOLOX and the pretrained model could be downloaded from here.
Training Data
The model was fine-tuned on around 17,000 TIER IV internal images of Japanese traffic lights.
Trained Onnx model
You can download the ONNX file using these instructions. Please visit autoware-documentation for more information.
Inner-workings / Algorithms
Based on the camera image and the global ROI array detected by map_based_detection node, a CNN-based detection method enables highly accurate traffic light detection.
Inputs / Outputs
Input
| Name | Type | Description |
|---|---|---|
~/input/image |
sensor_msgs/Image |
The full size camera image |
~/input/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector |
~/expect/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector without any offset |
Output
| Name | Type | Description |
|---|---|---|
~/output/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The detected accurate rois |
~/debug/exe_time_ms |
tier4_debug_msgs::msg::Float32Stamped |
The time taken for inference |
Parameters
Core Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
fine_detector_score_thresh |
double | 0.3 | If the objectness score is less than this value, the object is ignored |
fine_detector_nms_thresh |
double | 0.65 | IoU threshold to perform Non-Maximum Suppression |
Node Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
data_path |
string | ”$(env HOME)/autoware_data” | packages data and artifacts directory path |
fine_detector_model_path |
string | ”” | The onnx file name for yolo model |
fine_detector_label_path |
string | ”” | The label file with label names for detected objects written on it |
fine_detector_precision |
string | “fp32” | The inference mode: “fp32”, “fp16” |
approximate_sync |
bool | false | Flag for whether to ues approximate sync policy |
Assumptions / Known limits
Reference repositories
YOLOX github repository
Package Dependencies
| Deps | Name |
|---|---|
| autoware_cmake | |
| ament_cmake_auto | |
| autoware_lint_common | |
| cv_bridge | |
| image_transport | |
| message_filters | |
| rclcpp | |
| rclcpp_components | |
| sensor_msgs | |
| tensorrt_yolox | |
| tier4_debug_msgs | |
| tier4_perception_msgs |
System Dependencies
Dependant Packages
| Name | Deps |
|---|---|
| tier4_perception_launch |
Launch files
- launch/traffic_light_fine_detector.launch.xml
-
- data_path [default: $(env HOME)/autoware_data]
- fine_detector_label_path [default: $(var data_path)/traffic_light_fine_detector/tlr_labels.txt]
- fine_detector_model_path [default: $(var data_path)/traffic_light_fine_detector/tlr_yolox_s_batch_6.onnx]
- fine_detector_precision [default: fp16]
- fine_detector_score_thresh [default: 0.3]
- fine_detector_nms_thresh [default: 0.65]
- input/image [default: /image_raw]
- input/rois [default: /traffic_light_map_based_detector/output/rois]
- expect/rois [default: ~/expect/rois]
- output/rois [default: ~/output/rois]
- build_only [default: false]
Messages
Services
Plugins
Recent questions tagged traffic_light_fine_detector at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache License 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Tao Zhong
- Shunsuke Miura
Authors
traffic_light_fine_detector
Purpose
It is a package for traffic light detection using YoloX-s.
Training Information
Pretrained Model
The model is based on YOLOX and the pretrained model could be downloaded from here.
Training Data
The model was fine-tuned on around 17,000 TIER IV internal images of Japanese traffic lights.
Trained Onnx model
You can download the ONNX file using these instructions. Please visit autoware-documentation for more information.
Inner-workings / Algorithms
Based on the camera image and the global ROI array detected by map_based_detection node, a CNN-based detection method enables highly accurate traffic light detection.
Inputs / Outputs
Input
| Name | Type | Description |
|---|---|---|
~/input/image |
sensor_msgs/Image |
The full size camera image |
~/input/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector |
~/expect/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector without any offset |
Output
| Name | Type | Description |
|---|---|---|
~/output/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The detected accurate rois |
~/debug/exe_time_ms |
tier4_debug_msgs::msg::Float32Stamped |
The time taken for inference |
Parameters
Core Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
fine_detector_score_thresh |
double | 0.3 | If the objectness score is less than this value, the object is ignored |
fine_detector_nms_thresh |
double | 0.65 | IoU threshold to perform Non-Maximum Suppression |
Node Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
data_path |
string | ”$(env HOME)/autoware_data” | packages data and artifacts directory path |
fine_detector_model_path |
string | ”” | The onnx file name for yolo model |
fine_detector_label_path |
string | ”” | The label file with label names for detected objects written on it |
fine_detector_precision |
string | “fp32” | The inference mode: “fp32”, “fp16” |
approximate_sync |
bool | false | Flag for whether to ues approximate sync policy |
Assumptions / Known limits
Reference repositories
YOLOX github repository
Package Dependencies
| Deps | Name |
|---|---|
| autoware_cmake | |
| ament_cmake_auto | |
| autoware_lint_common | |
| cv_bridge | |
| image_transport | |
| message_filters | |
| rclcpp | |
| rclcpp_components | |
| sensor_msgs | |
| tensorrt_yolox | |
| tier4_debug_msgs | |
| tier4_perception_msgs |
System Dependencies
Dependant Packages
| Name | Deps |
|---|---|
| tier4_perception_launch |
Launch files
- launch/traffic_light_fine_detector.launch.xml
-
- data_path [default: $(env HOME)/autoware_data]
- fine_detector_label_path [default: $(var data_path)/traffic_light_fine_detector/tlr_labels.txt]
- fine_detector_model_path [default: $(var data_path)/traffic_light_fine_detector/tlr_yolox_s_batch_6.onnx]
- fine_detector_precision [default: fp16]
- fine_detector_score_thresh [default: 0.3]
- fine_detector_nms_thresh [default: 0.65]
- input/image [default: /image_raw]
- input/rois [default: /traffic_light_map_based_detector/output/rois]
- expect/rois [default: ~/expect/rois]
- output/rois [default: ~/output/rois]
- build_only [default: false]
Messages
Services
Plugins
Recent questions tagged traffic_light_fine_detector at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache License 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Tao Zhong
- Shunsuke Miura
Authors
traffic_light_fine_detector
Purpose
It is a package for traffic light detection using YoloX-s.
Training Information
Pretrained Model
The model is based on YOLOX and the pretrained model could be downloaded from here.
Training Data
The model was fine-tuned on around 17,000 TIER IV internal images of Japanese traffic lights.
Trained Onnx model
You can download the ONNX file using these instructions. Please visit autoware-documentation for more information.
Inner-workings / Algorithms
Based on the camera image and the global ROI array detected by map_based_detection node, a CNN-based detection method enables highly accurate traffic light detection.
Inputs / Outputs
Input
| Name | Type | Description |
|---|---|---|
~/input/image |
sensor_msgs/Image |
The full size camera image |
~/input/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector |
~/expect/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The array of ROIs detected by map_based_detector without any offset |
Output
| Name | Type | Description |
|---|---|---|
~/output/rois |
tier4_perception_msgs::msg::TrafficLightRoiArray |
The detected accurate rois |
~/debug/exe_time_ms |
tier4_debug_msgs::msg::Float32Stamped |
The time taken for inference |
Parameters
Core Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
fine_detector_score_thresh |
double | 0.3 | If the objectness score is less than this value, the object is ignored |
fine_detector_nms_thresh |
double | 0.65 | IoU threshold to perform Non-Maximum Suppression |
Node Parameters
| Name | Type | Default Value | Description |
|---|---|---|---|
data_path |
string | ”$(env HOME)/autoware_data” | packages data and artifacts directory path |
fine_detector_model_path |
string | ”” | The onnx file name for yolo model |
fine_detector_label_path |
string | ”” | The label file with label names for detected objects written on it |
fine_detector_precision |
string | “fp32” | The inference mode: “fp32”, “fp16” |
approximate_sync |
bool | false | Flag for whether to ues approximate sync policy |
Assumptions / Known limits
Reference repositories
YOLOX github repository
Package Dependencies
| Deps | Name |
|---|---|
| autoware_cmake | |
| ament_cmake_auto | |
| autoware_lint_common | |
| cv_bridge | |
| image_transport | |
| message_filters | |
| rclcpp | |
| rclcpp_components | |
| sensor_msgs | |
| tensorrt_yolox | |
| tier4_debug_msgs | |
| tier4_perception_msgs |
System Dependencies
Dependant Packages
| Name | Deps |
|---|---|
| tier4_perception_launch |
Launch files
- launch/traffic_light_fine_detector.launch.xml
-
- data_path [default: $(env HOME)/autoware_data]
- fine_detector_label_path [default: $(var data_path)/traffic_light_fine_detector/tlr_labels.txt]
- fine_detector_model_path [default: $(var data_path)/traffic_light_fine_detector/tlr_yolox_s_batch_6.onnx]
- fine_detector_precision [default: fp16]
- fine_detector_score_thresh [default: 0.3]
- fine_detector_nms_thresh [default: 0.65]
- input/image [default: /image_raw]
- input/rois [default: /traffic_light_map_based_detector/output/rois]
- expect/rois [default: ~/expect/rois]
- output/rois [default: ~/output/rois]
- build_only [default: false]