YOLOX-Body-With-Wheelchair

Lightweight human detection models generated on high-quality human data sets. It can detect objects with high accuracy.

output_human_with_wheelchair.mp4

1. Test

• Python 3.10

• onnx 1.14.1+

• onnxruntime-gpu v1.16.1 (TensorRT Execution Provider Enabled Binary. See: onnxruntime-gpu v1.16.1 + CUDA 11.8 + TensorRT 8.5.3 build (RTX3070))

• opencv-contrib-python 4.9.0.80

• numpy 1.24.3

• TensorRT 8.5.3-1+cuda11.8

  # Common ############################################
  pip install opencv-contrib-python numpy onnx
  
  # For ONNX ##########################################
  pip uninstall onnxruntime onnxruntime-gpu
  
  pip install onnxruntime
  or
  pip install onnxruntime-gpu

• Demonstration of models with built-in post-processing (Float32/Float16)

  usage:
    demo_yolox_onnx_humanwithwheelchair.py \
    [-h] \
    [-m MODEL] \
    (-v VIDEO | -i IMAGES_DIR) \
    [-ep {cpu,cuda,tensorrt}] \
    [-dvw] \
    [-dwk]
  
  options:
    -h, --help
      show this help message and exit
    -m MODEL, --model MODEL
      ONNX/TFLite file path for YOLOX.
    -v VIDEO, --video VIDEO
      Video file path or camera index.
    -i IMAGES_DIR, --images_dir IMAGES_DIR
      jpg, png images folder path.
    -ep {cpu,cuda,tensorrt}, \
        --execution_provider {cpu,cuda,tensorrt}
      Execution provider for ONNXRuntime.
    -dvw, --disable_video_writer
      Disable video writer. Eliminates the file I/O load associated with automatic
      recording to MP4. Devices that use a MicroSD card or similar for main
      storage can speed up overall processing.
    -dwk, --disable_waitKey
      Disable cv2.waitKey(). When you want to process a batch of still images,
      disable key-input wait and process them continuously.
  

• YOLOX-Body-With-Wheelchair - Nano

  Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.763
  Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.983
  Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.934
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
  Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.344
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.768
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.634
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.794
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.794
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.700
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.795
  per class AP:
  | class                | AP     |
  |:---------------------|:-------|
  | body-with-wheelchair | 76.334 |
  per class AR:
  | class                | AR     |
  |:---------------------|:-------|
  | body-with-wheelchair | 79.375 |
  

• YOLOX-Body-With-Wheelchair - Tiny

  Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.763
  Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.971
  Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.931
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
  Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.600
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.769
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.647
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.809
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.809
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.600
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.813
  per class AP:
  | class                | AP     |
  |:---------------------|:-------|
  | body-with-wheelchair | 76.307 |
  per class AR:
  | class                | AR     |
  |:---------------------|:-------|
  | body-with-wheelchair | 80.938 |
  

• YOLOX-Body-With-Wheelchair - S

  Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.822
  Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.991
  Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.972
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
  Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.250
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.828
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.694
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.853
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.853
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.500
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.859
  per class AP:
  | class                | AP     |
  |:---------------------|:-------|
  | body-with-wheelchair | 82.183 |
  per class AR:
  | class                | AR     |
  |:---------------------|:-------|
  | body-with-wheelchair | 85.312 |
  

• YOLOX-Body-With-Wheelchair - M

  Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.877
  Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.995
  Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.956
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
  Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.700
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.879
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.706
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.900
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.900
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.700
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.903
  per class AP:
  | class                | AP     |
  |:---------------------|:-------|
  | body-with-wheelchair | 87.668 |
  per class AR:
  | class                | AR     |
  |:---------------------|:-------|
  | body-with-wheelchair | 90.000 |
  

• YOLOX-Body-With-Wheelchair - L

  Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.882
  Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.997
  Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.978
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
  Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.600
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.885
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.731
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.898
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.898
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.600
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.903
  per class AP:
  | class                | AP     |
  |:---------------------|:-------|
  | body-with-wheelchair | 88.160 |
  per class AR:
  | class                | AR     |
  |:---------------------|:-------|
  | body-with-wheelchair | 89.844 |
  

• YOLOX-Body-With-Wheelchair - X

  Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.924
  Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.997
  Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.997
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
  Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.700
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.928
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.750
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.934
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.934
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.700
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.938
  per class AP:
  | class                | AP     |
  |:---------------------|:-------|
  | body-with-wheelchair | 92.407 |
  per class AR:
  | class                | AR     |
  |:---------------------|:-------|
  | body-with-wheelchair | 93.438 |
  

• Post-Process

  Because I add my own post-processing to the end of the model, which can be inferred by TensorRT, CUDA, and CPU, the benchmarked inference speed is the end-to-end processing speed including all pre-processing and post-processing. EfficientNMS in TensorRT is very slow and should be offloaded to the CPU.

  • NMS default parameter

    param	value	note
    max_output_boxes_per_class	20	Maximum number of outputs per class of one type. 20 indicates that the maximum number of people detected is 20, the maximum number of heads detected is 20, and the maximum number of hands detected is 20. The larger the number, the more people can be detected, but the inference speed slows down slightly due to the larger overhead of NMS processing by the CPU. In addition, as the number of elements in the final output tensor increases, the amount of information transferred between hardware increases, resulting in higher transfer costs on the hardware circuit. Therefore, it would be desirable to set the numerical size to the minimum necessary.
    iou_threshold	0.40	A value indicating the percentage of occlusion allowed for multiple bounding boxes of the same class. 0.40 is excluded from the detection results if, for example, two bounding boxes overlap in more than 41% of the area. The smaller the value, the more occlusion is tolerated, but over-detection may increase.
    score_threshold	0.25	Bounding box confidence threshold. Specify in the range of 0.00 to 1.00. The larger the value, the stricter the filtering and the lower the NMS processing load, but in exchange, all but bounding boxes with high confidence values are excluded from detection. This is a parameter that has a very large percentage impact on NMS overhead.

  • Change NMS parameters

    Use PINTO0309/sam4onnx to rewrite the NonMaxSuppression parameter in the ONNX file.

    For example,

    pip install onnxsim==0.4.33 \
    && pip install -U simple-onnx-processing-tools \
    && pip install -U onnx \
    && python -m pip install -U onnx_graphsurgeon \
        --index-url https://pypi.ngc.nvidia.com
    
    ### max_output_boxes_per_class
    ### Example of changing the maximum number of detections per class to 100.
    sam4onnx \
    --op_name main01_nonmaxsuppression11 \
    --input_onnx_file_path yolox_s_body_head_hand_post_0299_0.4983_1x3x256x320.onnx \
    --output_onnx_file_path yolox_s_body_head_hand_post_0299_0.4983_1x3x256x320.onnx \
    --input_constants main01_max_output_boxes_per_class int64 [100]
    
    ### iou_threshold
    ### Example of changing the allowable area of occlusion to 20%.
    sam4onnx \
    --op_name main01_nonmaxsuppression11 \
    --input_onnx_file_path yolox_s_body_head_hand_post_0299_0.4983_1x3x256x320.onnx \
    --output_onnx_file_path yolox_s_body_head_hand_post_0299_0.4983_1x3x256x320.onnx \
    --input_constants main01_iou_threshold float32 [0.20]
    
    ### score_threshold
    ### Example of changing the bounding box score threshold to 15%.
    sam4onnx \
    --op_name main01_nonmaxsuppression11 \
    --input_onnx_file_path yolox_s_body_head_hand_post_0299_0.4983_1x3x256x320.onnx \
    --output_onnx_file_path yolox_s_body_head_hand_post_0299_0.4983_1x3x256x320.onnx \
    --input_constants main01_score_threshold float32 [0.15]

  • Post-processing structure

    PyTorch alone cannot generate this post-processing.

    

• INT8 quantization (TexasInstruments/YOLOX-ti-lite)

  In my experience, YOLOX has a very large accuracy degradation during quantization due to its structure. The reasons for this and the workaround are examined in detail by TexasInstruments. I have summarized the main points below on how to minimize accuracy degradation during quantization through my own practice. I just put into practice what TexasInstruments suggested, but the degrade in accuracy during quantization was extremely small. Note, however, that the results of the Float16 mixed-precision training before quantization are significantly degraded in accuracy due to the change in activation function to ReLU and many other workarounds, as well as the completely different data sets being benchmarked.

  https://github.com/PINTO0309/onnx2tf?tab=readme-ov-file#7-if-the-accuracy-of-the-int8-quantized-model-degrades-significantly

4. Citiation

If this work has contributed in any way to your research or business, I would be happy to be cited in your literature.

@software{YOLOX-Body-With-Wheelchair,
  author={Katsuya Hyodo},
  title={Lightweight human detection models generated on high-quality human data sets. It can detect objects with high accuracy.},
  url={https://github.com/PINTO0309/PINTO_model_zoo/tree/main/446_YOLOX-Body-With-Wheelchair},
  year={2024},
  month={2},
  doi={10.5281/zenodo.10229410}
}

5. Cited

I am very grateful for their excellent work.

• COCO-Hand

  https://vision.cs.stonybrook.edu/~supreeth/

  @article{Hand-CNN,
    title={Contextual Attention for Hand Detection in the Wild},
    author={Supreeth Narasimhaswamy and Zhengwei Wei and Yang Wang and Justin Zhang and Minh Hoai},
    booktitle={International Conference on Computer Vision (ICCV)},
    year={2019},
    url={https://arxiv.org/pdf/1904.04882.pdf}
  }

• CD-COCO: Complex Distorted COCO database for Scene-Context-Aware computer vision

  

  @INPROCEEDINGS{10323035,
    author={Beghdadi, Ayman and Beghdadi, Azeddine and Mallem, Malik and Beji, Lotfi and Cheikh, Faouzi Alaya},
    booktitle={2023 11th European Workshop on Visual Information Processing (EUVIP)},
    title={CD-COCO: A Versatile Complex Distorted COCO Database for Scene-Context-Aware Computer Vision},
    year={2023},
    volume={},
    number={},
    pages={1-6},
    doi={10.1109/EUVIP58404.2023.10323035}
  }

• YOLOX

  https://github.com/Megvii-BaseDetection/YOLOX

  @article{yolox2021,
    title={YOLOX: Exceeding YOLO Series in 2021},
    author={Ge, Zheng and Liu, Songtao and Wang, Feng and Li, Zeming and Sun, Jian},
    journal={arXiv preprint arXiv:2107.08430},
    year={2021}
  }

• YOLOX-ti-lite

  https://github.com/TexasInstruments/edgeai-yolox

• yolox-ti-lite_tflite

  https://github.com/motokimura/yolox-ti-lite_tflite

• YOLOX-Colaboratory-Training-Sample

  高橋かずひと https://github.com/Kazuhito00

  https://github.com/Kazuhito00/YOLOX-Colaboratory-Training-Sample

6. License

Apache License Version 2.0