Pedestrian detection network based on SSD framework with tuned MobileNet v1 as a feature extractor. Some layers of MobileNet v1 are binary and use I1 arithm
Metric | Value |
---|---|
Average Precision (AP) | 84% |
Target pedestrian size | 60 x 120 pixels on Full HD image |
Max objects to detect | 200 |
GFlops | 0.750 |
GI1ops | 2.086 |
MParams | 1.165 |
Source framework | Pytorch* |
Average Precision metric described in: Mark Everingham et al. “The PASCAL Visual Object Classes (VOC) Challenge”.
Tested on an internal dataset with 1001 pedestrian to detect.
image_id
, label
, conf
, x_min
, y_min
, x_max
, y_max
]image_id
- ID of the image in the batchlabel
- predicted class IDconf
- confidence for the predicted classx_min
, y_min
) - coordinates of the top left bounding box cornerx_max
, y_max
) - coordinates of the bottom right bounding box corner.[*] Other names and brands may be claimed as the property of others.
The net is tuned from pedestrian-detection-adas-0002.