文件列表:

3rd_party (0, 2017-03-13)
3rd_party\DP_NMS (0, 2017-03-13)
3rd_party\DP_NMS\build_graph.m (942, 2017-03-13)
3rd_party\DP_NMS\calc_overlap.m (1134, 2017-03-13)
3rd_party\DP_NMS\cs2_func.m (717, 2017-03-13)
3rd_party\DP_NMS\evaluateTracking.m (5059, 2017-03-13)
3rd_party\DP_NMS\globals.m (832, 2017-03-13)
3rd_party\DP_NMS\main.m (2663, 2017-03-13)
3rd_party\DP_NMS\nms_aggressive.m (453, 2017-03-13)
3rd_party\DP_NMS\sub.m (191, 2017-03-13)
3rd_party\DP_NMS\tracking_dp.m (1763, 2017-03-13)
3rd_party\DP_NMS\tracking_push_relabel.m (3229, 2017-03-13)
3rd_party\DP_NMS\write_tracking_results.m (464, 2017-03-13)
3rd_party\Hungarian (0, 2017-03-13)
3rd_party\Hungarian\assignment.h (462, 2017-03-13)
3rd_party\Hungarian\assignment.html (7052, 2017-03-13)
3rd_party\Hungarian\assignmentallpossible.m (4426, 2017-03-13)
3rd_party\Hungarian\assignmentoptimal.c (13571, 2017-03-13)
3rd_party\Hungarian\assignmentoptimal.m (8280, 2017-03-13)
3rd_party\Hungarian\assignmentoptimal.mexa64 (12869, 2017-03-13)
3rd_party\Hungarian\assignmentsuboptimal1.c (6872, 2017-03-13)
3rd_party\Hungarian\assignmentsuboptimal1.m (5141, 2017-03-13)
3rd_party\Hungarian\assignmentsuboptimal1.mexa64 (12452, 2017-03-13)
3rd_party\Hungarian\assignmentsuboptimal2.c (2291, 2017-03-13)
3rd_party\Hungarian\assignmentsuboptimal2.m (1952, 2017-03-13)
3rd_party\Hungarian\assignmentsuboptimal2.mexa64 (8326, 2017-03-13)
3rd_party\Hungarian\license.txt (1314, 2017-03-13)
3rd_party\Hungarian\testassignment.m (5022, 2017-03-13)
3rd_party\L1APG (0, 2017-03-13)
3rd_party\L1APG\APGLASSOup.m (1384, 2017-03-13)
3rd_party\L1APG\IMGaffine_c.c (3778, 2017-03-13)
3rd_party\L1APG\IMGaffine_c.mexa64 (12705, 2017-03-13)
3rd_party\L1APG\InitTemplates.m (1049, 2017-03-13)
3rd_party\L1APG\L1APG_initialize.m (1674, 2017-03-13)
3rd_party\L1APG\L1APG_reconstruction_error.m (755, 2017-03-13)
3rd_party\L1APG\L1APG_track_frame.m (4559, 2017-03-13)
3rd_party\L1APG\L1APG_update.m (2331, 2017-03-13)
3rd_party\L1APG\aff2image.m (800, 2017-03-13)
... ...

# Learning to Track: Online Multi-Object Tracking by Decision Making Created by Yu Xiang at CVGL, Stanford University. ### Introduction **MDP_Tracking** is a online multi-object tracking framework based on Markov Decision Processes (MDPs). http://cvgl.stanford.edu/projects/MDP_tracking/ ### License MDP_Tracking is released under the MIT License (refer to the LICENSE file for details). ### Citation If you find MDP_Tracking useful in your research, please consider citing: @inproceedings{xiang2015learning, Author = {Xiang, Yu and Alahi, Alexandre and Savarese, Silvio}, Title = {Learning to Track: Online Multi-Object Tracking by Decision Making}, Booktitle = {International Conference on Computer Vision (ICCV)}, Year = {2015} } ### Usage on the 2D MOT benchmark 1. Download the 2D MOT benchmark (data and development kit) from https://motchallenge.net/data/2D_MOT_2015/ 2. Set the path of the MOT dataset in global.m 3. Run compile.m. OpenCV is needed. 4. For validataion, use MOT_cross_validation.m 5. For testing, use MOT_test.m We provide our own detection using SubCNN [1] on the 2D MOT 2015 dataset [here](https://drive.google.com/open?id=0B4WdmTHU8V7VeVlISVhMNjQ3N1k). Important: make sure libsvm-3.20 in the 3rd_party directory is used. Other versions of libsvm may not be compatible with the code. ### Usage on the KITTI tracking dataset 1. Download the KITTI tracking benchmark (data, development kit and detections) from http://www.cvlibs.net/datasets/kitti/eval_tracking.php 2. Check out the kitti branch ```Shell git checkout kitti ``` 3. Set the path of the KITTI tracking dataset in global.m 4. Run compile.m. OpenCV is needed. 5. For validataion, use KITTI_cross_validation.m 6. For testing, use KITTI_test.m We provide our own detection using SubCNN [1] on the KITTI tracking dataset [here](https://drive.google.com/open?id=0B4WdmTHU8V7Vd29GeFBqdl9yQXM). ### References [1] Y. Xiang, W. Choi, Y. Lin and S. Savarese. Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection. In IEEE Winter Conference on Applications of Computer Vision (WACV), 2017. ### Contact If you find any bug or issue of the software, please contact yuxiang at umich dot edu

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：