Paper Info
Title
Latent subcategory models for pedestrian detection with partial occlusion handling
Abstract
Pedestrian detection is one of the most important tasks in Computer Vision, especially in automotive and security applications. One of the most common problems in real scenarios is related to the detection of occluded pedestrians. In this paper, we propose a novel multi-cue pedestrian detection approach able to deal with non homogeneous object samples by learning latent subcategory models trained on both visual and depth-based features. We also propose a novel self-similarity based feature, namely SST <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">D</sub> , to encode the homogeneity in appearance of pedestrians characterized by similar occlusion patterns. Experiments are performed on the Daimler Pedestrian Detection Benchmark Dataset showing the robustness of our approach in actual scenarios.
Year
DOI
Venue
2015
10.1109/AVSS.2015.7301786
2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
Keywords
Field
DocType
latent subcategory model,partial occlusion handling,computer vision,multicue pedestrian detection,self-similarity based feature,homogeneity encoding,similar occlusion patterns,Daimler pedestrian detection benchmark dataset
Computer vision,Subcategory,Pattern recognition,Object-class detection,Feature (computer vision),Computer science,Support vector machine,Robustness (computer science),Feature extraction,Artificial intelligence,Pedestrian detection,Benchmark (computing)
Conference
Citations 
PageRank 
References 
0
0.34
24
Authors
3
Name
Order
Citations
PageRank
Samuele Martelli1314.77
Marco San-Biagio2404.46
Vittorio Murino33277207.20