Robotics and Computer Vision Lab

Publications

International Conference
2014.10.25 12:21

A Two Phase Approach for Pedestrian Detection

조회 수 1009 댓글 0
Extra Form
저 자 Soonmin Hwang, Tae-Hyun Oh, In So Kweon
학 회 The 12th Asian Conference on Computer Vision Workshops (ACCV Workshops)
Notes <Acknowledgement > This work was supported by the Development of Autonomous Emergency Braking System for Pedestrian Protection project funded by the Ministry of Trade, Industry and Energy of Korea. (MOTIE)(No.10044775)
논문일시(Year) 2014
논문일시(Month) 11
Most of current pedestrian detectors have pursued high detection rate without carefully considering sample distributions. In this paper, we argue that the following characteristics must be considered; 1)large intra-class variation of pedestrians (multi-modality), and 2) data imbalance between positives and negatives. Pedestrian detection can be regarded as one of nding needles in a haystack problems (rare class detection). Inspired by a rare class detection technique, we propose a two-phase classi er integrating an existing baseline detector and a hard negative expert by separately conquering recall and precision. Main idea behind the hard negative expert is to reduce sample space to be learned, so that informative decision boundaries can be e ectively learned. The multi-modality problem is dealt with a simple variant of a LDA based random forests as the hard negative expert. We optimally integrate two models by learned integration rules. By virtue of the two-phase structure, our method achieve competitive performance with only little additional computation. Our approach achieves 38.44% mean miss-rate for the reasonable setting of Caltech Pedestrian Benchmark.

List of Articles
224. Accurate Depth Map Estimation from a Lenslet Light Field Camera
Hae-Gon Jeon, Jaesik Park, Gyeongmin Choe, Jinsun Park, Yunsu Bok, Yu-Wing Tai, In So Kweon
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2015 / 06
223. Fast Randomized Singular Value Thresholding for Nuclear Norm Minimization
Tae-Hyun Oh, Yasuyuki Matsushita, Yu-Wing Tai, In So Kweon
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2015 / 06
222. Multispectral Pedestrian Detection: Benchmark Dataset and Baselines
Soonmin Hwang, Jaesik Park, Namil Kim, Yukyung Choi, In So Kweon
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2015 / 06
221. Specular Reflection Separation Using Dark Channel Prior
Hyeongwoo Kim, Hailin Jin, Sunil Hadap, In So Kweon
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2013 / 06
220. Hybrid vision-based SLAM coupled with moving object tracking
Jihong Min, Jungho Kim, Hyeongwoo Kim, Kiho Kwak, In So Kweon
International Conference on Robotics & Automation (ICRA) 2014 / 05
» A Two Phase Approach for Pedestrian Detection
Soonmin Hwang, Tae-Hyun Oh, In So Kweon
The 12th Asian Conference on Computer Vision Workshops (ACCV Workshops) 2014 / 11
218. Robust Binary Feature Using Intensity Order
Yukyung Choi, Chaehoon Park, Joon-Young Lee, In So Kweon
The 12th Asian Conference on Computer Vision (ACCV) 2014 / 11
217. Accelerated kmeans Clustering using Binary Random Projection
Yukyung Choi, Chaehoon Park, In So Kweon
The 12th Asian Conference on Computer Vision (ACCV) 2014 / 11
216. Real-time Head Orientation from a Monocular Camera using Deep Neural Network
Byungtae Ahn, Jaesik Park, In So Kweon
The 12th Asian Conference on Computer Vision (ACCV) 2014 / 11
215. Motion Deblurring using Coded Exposure for a Wheeled Mobile Robot
Kibaek Park, Seunghak Shin, Hae-Gon Jeon, Joon-Young Lee, In So Kweon
The 11th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) 2014 / 11
214. RGBD Sensor and Mirrors: a Practical Setup for 3D Reconstruction of Dynamic Objects
Min-Hyun Kim, Jaesik Park, In So Kweon
The 11th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) 2014 / 11
213. A Simple and Real-Time Moving Object Detection Invariant to Cast Shadow
Tae-Hyun Oh, In So Kweon
The 11th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) 2014 / 11
212. A Fusion Approach for Robust Visual Object Tracking in Crowd Scenes
Tae-Hyun Oh, Kyungdon Joo, Junsik Kim, Jaesik Park, In So Kweon
The 11th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) 2014 / 11
211. Geometric Calibration of Micro-Lens-Based Light-Field Cameras using Line Features
Yunsu Bok, Hae-Gon Jeon, In So Kweon
European Conference on Computer Vision (ECCV) 2014 / 09
210. Extrinsic Calibration of 2D Laser Sensors
Dong-Geol Choi, Yunsu Bok, Jun-sik Kim, In So Kweon
International Conference on Robotics & Automation (ICRA) 2014 / 05
209. Extrinsic Calibration of Non-overlapping Camera-Laser System using Structured Environment
Yunsu Bok, Dong-Geol Choi, Pascal Vasseur, In So Kweon
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2014 / 09
208. GMM-based Saliency Aggregation for Calibration-free Gaze Estimation
Jinsoo Choi, Byungtae Ahn, Jaesik Park, In So Kweon
International Conference on Image Processing (ICIP) 2014 / 10
207. Cost-Aware Depth Map Estimation for Lytro Camera
Min Jung Kim, Tae-Hyun Oh, In So Kweon
International Conference on Image Processing (ICIP) 2014 / 10
206. Balanced Optical Flow Refinement by Bidirectional Constraint
Jongwon Choi, Hyeongwoo Kim, Tae-Hyun Oh, In So Kweon
International Conference on Image Processing (ICIP) 2014 / 10
205. Auto-adjusting Camera Exposure for Outdoor Robotics using Gradient Information
Inwook Shim, Joon-Young Lee, In So Kweon
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2014 / 09
Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 ... 17 Next
/ 17