A Conditional Entropy-Based Independent Component Analysis for Applications in Human Detection and Tracking
<p>Abstract</p> <p>We present in this paper a modified independent component analysis (mICA) based on the conditional entropy to discriminate unsorted independent components. We make use of the conditional entropy to select an appropriate subset of the ICA features with superior ca...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2010-01-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Online Access: | http://asp.eurasipjournals.com/content/2010/468329 |
| _version_ | 1818009228673024000 |
|---|---|
| author | Shou Yu-Wen Lin Chin-Teng Siana Linda Shen Tzu-Kuei |
| author_facet | Shou Yu-Wen Lin Chin-Teng Siana Linda Shen Tzu-Kuei |
| author_sort | Shou Yu-Wen |
| collection | DOAJ |
| description | <p>Abstract</p> <p>We present in this paper a modified independent component analysis (mICA) based on the conditional entropy to discriminate unsorted independent components. We make use of the conditional entropy to select an appropriate subset of the ICA features with superior capability in classification and apply support vector machine (SVM) to recognizing patterns of human and nonhuman. Moreover, we use the models of background images based on Gaussian mixture model (GMM) to handle images with complicated backgrounds. Also, the color-based shadow elimination and head models in ellipse shapes are combined to improve the performance of moving objects extraction and recognition in our system. Our proposed tracking mechanism monitors the movement of humans, animals, or vehicles within a surveillance area and keeps tracking the moving pedestrians by using the color information in HSV domain. Our tracking mechanism uses the Kalman filter to predict locations of moving objects for the conditions in lack of color information of detected objects. Finally, our experimental results show that our proposed approach can perform well for real-time applications in both indoor and outdoor environments.</p> |
| first_indexed | 2024-04-14T05:40:17Z |
| format | Article |
| id | doaj.art-84de44cda1d444398905f248814e1c81 |
| institution | Directory Open Access Journal |
| issn | 1687-6172 1687-6180 |
| language | English |
| last_indexed | 2024-04-14T05:40:17Z |
| publishDate | 2010-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-84de44cda1d444398905f248814e1c812022-12-22T02:09:29ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61721687-61802010-01-0120101468329A Conditional Entropy-Based Independent Component Analysis for Applications in Human Detection and TrackingShou Yu-WenLin Chin-TengSiana LindaShen Tzu-Kuei<p>Abstract</p> <p>We present in this paper a modified independent component analysis (mICA) based on the conditional entropy to discriminate unsorted independent components. We make use of the conditional entropy to select an appropriate subset of the ICA features with superior capability in classification and apply support vector machine (SVM) to recognizing patterns of human and nonhuman. Moreover, we use the models of background images based on Gaussian mixture model (GMM) to handle images with complicated backgrounds. Also, the color-based shadow elimination and head models in ellipse shapes are combined to improve the performance of moving objects extraction and recognition in our system. Our proposed tracking mechanism monitors the movement of humans, animals, or vehicles within a surveillance area and keeps tracking the moving pedestrians by using the color information in HSV domain. Our tracking mechanism uses the Kalman filter to predict locations of moving objects for the conditions in lack of color information of detected objects. Finally, our experimental results show that our proposed approach can perform well for real-time applications in both indoor and outdoor environments.</p>http://asp.eurasipjournals.com/content/2010/468329 |
| spellingShingle | Shou Yu-Wen Lin Chin-Teng Siana Linda Shen Tzu-Kuei A Conditional Entropy-Based Independent Component Analysis for Applications in Human Detection and Tracking EURASIP Journal on Advances in Signal Processing |
| title | A Conditional Entropy-Based Independent Component Analysis for Applications in Human Detection and Tracking |
| title_full | A Conditional Entropy-Based Independent Component Analysis for Applications in Human Detection and Tracking |
| title_fullStr | A Conditional Entropy-Based Independent Component Analysis for Applications in Human Detection and Tracking |
| title_full_unstemmed | A Conditional Entropy-Based Independent Component Analysis for Applications in Human Detection and Tracking |
| title_short | A Conditional Entropy-Based Independent Component Analysis for Applications in Human Detection and Tracking |
| title_sort | conditional entropy based independent component analysis for applications in human detection and tracking |
| url | http://asp.eurasipjournals.com/content/2010/468329 |
| work_keys_str_mv | AT shouyuwen aconditionalentropybasedindependentcomponentanalysisforapplicationsinhumandetectionandtracking AT linchinteng aconditionalentropybasedindependentcomponentanalysisforapplicationsinhumandetectionandtracking AT sianalinda aconditionalentropybasedindependentcomponentanalysisforapplicationsinhumandetectionandtracking AT shentzukuei aconditionalentropybasedindependentcomponentanalysisforapplicationsinhumandetectionandtracking AT shouyuwen conditionalentropybasedindependentcomponentanalysisforapplicationsinhumandetectionandtracking AT linchinteng conditionalentropybasedindependentcomponentanalysisforapplicationsinhumandetectionandtracking AT sianalinda conditionalentropybasedindependentcomponentanalysisforapplicationsinhumandetectionandtracking AT shentzukuei conditionalentropybasedindependentcomponentanalysisforapplicationsinhumandetectionandtracking |