题  目：New features and insights for effective pedestrian detection

报告人：Prof. Chunhua Shen (澳大利亚阿德雷德大学沈春华教授)

时  间：2014年6月24日（周二）15：30—17:00

地  点：屏峰校区郁B203

报告人简介:
     Chunhua Shen is a Professor at School of Computer Science, University of Adelaide. Before he joined University of Adelaide in 2011 as a Senior Lecturer, he was with the computer vision program at NICTA (National ICT Australia), Canberra Research Laboratory for about 6 years. His research interests are in the intersection of computer vision and statistical machine learning. Recent work has been on real-time object detection, large-scale image retrieval and classification, and scalable nonlinear optimization. He studied at Nanjing University, at Australian National University, and received his PhD degree from the University of Adelaide. From 2012 to 2016, he holds an Australian Research Council Future Fellowship.

内容摘要:

Real-time pedestrian detection in video is an important problem in computer vision, which has many applications such as automated driverless car. We propose a simple yet effective approach to the problem of human detection which outperforms the current state-of-the-art. Our new features are built on the basis of low-level visual features and spatial pooling. Incorporating spatial pooling improves the translational invariance and thus the robustness of the detection process. We then directly optimize the partial area under the ROC curve (PAUC) measure, which concentrates detection performance in the range of most practical importance. The combination of these factors leads to a pedestrian detector which outperforms all competitors on all of the standard benchmark datasets.

We advance state-of-the-art results by lowering the average miss rate from 13% to 11% on the INRIA benchmark, 41% to 38% on the ETH benchmark, 51% to 42% on the TUD-Brussels benchmark and 36% to 29% on the Caltech-USA benchmark.