Skip to content

Latest commit

 

History

History
70 lines (52 loc) · 2.57 KB

person-vehicle-bike-detection-crossroad-1016.md

File metadata and controls

70 lines (52 loc) · 2.57 KB

person-vehicle-bike-detection-crossroad-1016

Use Case and High-Level Description

MobileNetV2 + SSD-based network is for Person/Vehicle/Bike detection in security surveillance applications. Works in a variety of scenes and weather/lighting conditions.

Example

Specification

Metric Value
Mean Average Precision (mAP) 62.55%
AP people 73.63%
AP vehicles 77.84%
AP bikes 36.18%
Max objects to detect 200
GFlops 3.560
Source framework PyTorch

Average Precision (AP) is defined as an area under the precision/recall curve.

Validation dataset consists of 34,757 images from various scenes and includes:

Type of object Number of bounding boxes
Vehicle 229,503
Pedestrian 240,009
Non-vehicle 62,643

Similarly, training dataset has 219,181 images with:

Type of object Number of bounding boxes
Vehicle 810,323
Pedestrian 1,114,799
Non-vehicle 62,334

Performance

Inputs

  1. name: "input.1" , shape: [1x3x512x512] - An input image in the format [BxCxHxW], where

    • B - batch size
    • C - number of channels
    • H - image height
    • W - image width

    Expected color order: BGR.

Outputs

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 batch
  • label - predicted class ID
  • conf - confidence for the predicted class
  • (x_min, y_min) - coordinates of the top left bounding box corner
  • (x_max, y_max) - coordinates of the bottom right bounding box corner.

Legal information

[*] Other names and brands may be claimed as the property of others.