Person Retrieval in Surveillance Video using Height, Color and Gender

A person is commonly described by attributes like height, build, cloth color, cloth type, and gender. Such attributes are known as soft biometrics. They bridge the semantic gap between human description and person retrieval in surveillance video. The paper proposes a deep learning-based linear filtering approach for person retrieval using height, cloth color, and gender. The proposed approach uses Mask R-CNN for pixel-wise person segmentation. It removes background clutter and provides precise boundary around the person. Color and gender models are fine-tuned using AlexNet and the algorithm is tested on SoftBioSearch dataset. It achieves good accuracy for person retrieval using the semantic query in challenging conditions.

PDF Abstract 2018 15th 2019 PDF

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Person Retrieval SoftBioSearch SSD Average IOU 0.503 # 1
Person Retrieval SoftBioSearch Baseline - AvatarSearch Average IOU 0.290 # 3
Person Retrieval SoftBioSearch Mask R-CNN and AlexNet Average IOU 0.363 # 2

Methods


No methods listed for this paper. Add relevant methods here