This is a pedestrian detector based on backbone with hyper-feature + R-FCN for the Retail scenario.
|Pose coverage||Standing upright, parallel to image plane|
|Support of occluded pedestrians||YES|
|Min pedestrian height||80 pixels (on 1080p)|
|Max objects to detect||200|
Average Precision (AP) is defined as an area under the precision/recall curve. Validation dataset consists of ~50K of images from ~100 different scenes.
1, 3, 544, 992 in format
1, C, H, W, where:
C- number of channels
H- image height
W- image width
The expected channel order is
1x6- An image information [544, 992, 992/
The net outputs blob with shape:
1, 1, 200, 7 in the format
1, 1, N, 7, where
N is the number of detected bounding boxes. Each detection has the format [
image_id- ID of the image in the batch
label- predicted class ID (1 - person)
conf- confidence for the predicted class
y_min) - coordinates of the top left bounding box corner
y_max) - coordinates of the bottom right bounding box corner
[*] Other names and brands may be claimed as the property of others.