Direction Estimation of Pedestrian from Images
The capability of estimating the walking direction of people would be useful in many applications such as those involving autonomous cars and robots. We introduce an approach for estimating the walking direction of people from images, based on learning the correct classification of a still image by...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/7277 |
| _version_ | 1826212141369131008 |
|---|---|
| author | Shimizu, Hiroaki Poggio, Tomaso |
| author_facet | Shimizu, Hiroaki Poggio, Tomaso |
| author_sort | Shimizu, Hiroaki |
| collection | MIT |
| description | The capability of estimating the walking direction of people would be useful in many applications such as those involving autonomous cars and robots. We introduce an approach for estimating the walking direction of people from images, based on learning the correct classification of a still image by using SVMs. We find that the performance of the system can be improved by classifying each image of a walking sequence and combining the outputs of the classifier. Experiments were performed to evaluate our system and estimate the trade-off between number of images in walking sequences and performance. |
| first_indexed | 2024-09-23T15:16:42Z |
| id | mit-1721.1/7277 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:16:42Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/72772019-04-12T08:34:36Z Direction Estimation of Pedestrian from Images Shimizu, Hiroaki Poggio, Tomaso AI pedestrian walking direction classification SVM recognition human motion The capability of estimating the walking direction of people would be useful in many applications such as those involving autonomous cars and robots. We introduce an approach for estimating the walking direction of people from images, based on learning the correct classification of a still image by using SVMs. We find that the performance of the system can be improved by classifying each image of a walking sequence and combining the outputs of the classifier. Experiments were performed to evaluate our system and estimate the trade-off between number of images in walking sequences and performance. 2004-10-20T21:05:12Z 2004-10-20T21:05:12Z 2003-08-27 AIM-2003-020 CBCL-230 http://hdl.handle.net/1721.1/7277 en_US AIM-2003-020 CBCL-230 11 p. 784806 bytes 664353 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI pedestrian walking direction classification SVM recognition human motion Shimizu, Hiroaki Poggio, Tomaso Direction Estimation of Pedestrian from Images |
| title | Direction Estimation of Pedestrian from Images |
| title_full | Direction Estimation of Pedestrian from Images |
| title_fullStr | Direction Estimation of Pedestrian from Images |
| title_full_unstemmed | Direction Estimation of Pedestrian from Images |
| title_short | Direction Estimation of Pedestrian from Images |
| title_sort | direction estimation of pedestrian from images |
| topic | AI pedestrian walking direction classification SVM recognition human motion |
| url | http://hdl.handle.net/1721.1/7277 |
| work_keys_str_mv | AT shimizuhiroaki directionestimationofpedestrianfromimages AT poggiotomaso directionestimationofpedestrianfromimages |