Pedestrian and vehicle detection network based on MobileNet v1.0 + SSD.
Metric | Value |
---|---|
AP for pedestrians | 88% |
AP for vehicles | 90% |
Target pedestrian size | 60x120 pixels |
Target vehicle size | 40x30 pixels |
GFLOPS | 3.974 |
MParams | 1.650 |
Source framework | Caffe* |
Average Precision (AP) metric is described in: Mark Everingham et al. The PASCAL Visual Object Classes (VOC) Challenge.
Tested on challenging internal datasets with 1001 pedestrian and 12585 vehicles to detect.
Name: input
, shape: [1x3x384x672] - An input image in the format [BxCxHxW], where:
The net outputs blob with shape: [1, 1, N, 7], where N is the number of detected bounding boxes. Each detection has the format [image_id
, label
, conf
, x_min
, y_min
, x_max
, y_max
], where:
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.