This is a person detector that is based on MobileNetV2 backbone with two SSD heads from 1/16 and 1/8 scale feature maps and clustered prior boxes for 512x512 resolution.
|AP||91.21% (internal test set)|
|Pose coverage||Standing upright, parallel to image plane|
|Support of occluded persons||YES|
|Min person height||100 pixels (on 1080p)|
Average Precision (AP) is defined as an area under the precision/recall curve. Intersection over union threshold of 0.5 is used for matching.
input, shape: [1x3x512x512] - An input image in the format [BxCxHxW], where:
Expected color order is BGR.
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- ID of the image in the batch
label- predicted class ID
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.