Abstract
Motion History Images(MHI) are extensively being used to represent the history of temporal changes involved in the execution of an activity. Here the intensity of the pixels of a scalar valued image are varied, depending upon the motion history. MHI suffers from a very prominent drawback that when self-occluding or over-writing activities are encountered it fails to generate a vivid description of the course of that activity. This happens because when repetitive activities are performed, the current action overwrites or deletes the information of the previous action. In this paper, we have designed a methodology which has overcome this problem of conventional MHI. In our mechanism, we have used red, green and blue channels to represent human movement. Initially the pixel values of all the three channels are null. When any motion is detected at a particular pixel for the first time, then it is represented using MHIR. However, if a repetitive action is performed, then it is represented using MHIG and if overwriting action is thereafter continued for the second time, then MHIB is utilized. In this approach, the pixel intensities are varied in accordance with the basic MHI. Thus, using our methodology which uses multiple channels, MHI is not only capable of detecting the history of motion but is also made capable of representing overlapping repetitive actions.
Original language | English |
---|---|
Title of host publication | International Conference on Communication and Signal Processing, ICCSP 2013 - Proceedings |
Pages | 556-560 |
Number of pages | 5 |
DOIs | |
Publication status | Published - 09-09-2013 |
Externally published | Yes |
Event | 2nd International Conference on Communication and Signal Processing, ICCSP 2013 - Melmaruvathur, Tamilnadu, India Duration: 03-04-2013 → 05-04-2013 |
Conference
Conference | 2nd International Conference on Communication and Signal Processing, ICCSP 2013 |
---|---|
Country | India |
City | Melmaruvathur, Tamilnadu |
Period | 03-04-13 → 05-04-13 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Computer Networks and Communications
- Signal Processing
Cite this
}
A novel method to represent repetitive and overwriting activities in motion history images. / Gupta, Rahul; Jain, Arpit; Rana, Satakshi.
International Conference on Communication and Signal Processing, ICCSP 2013 - Proceedings. 2013. p. 556-560 6577116.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - A novel method to represent repetitive and overwriting activities in motion history images
AU - Gupta, Rahul
AU - Jain, Arpit
AU - Rana, Satakshi
PY - 2013/9/9
Y1 - 2013/9/9
N2 - Motion History Images(MHI) are extensively being used to represent the history of temporal changes involved in the execution of an activity. Here the intensity of the pixels of a scalar valued image are varied, depending upon the motion history. MHI suffers from a very prominent drawback that when self-occluding or over-writing activities are encountered it fails to generate a vivid description of the course of that activity. This happens because when repetitive activities are performed, the current action overwrites or deletes the information of the previous action. In this paper, we have designed a methodology which has overcome this problem of conventional MHI. In our mechanism, we have used red, green and blue channels to represent human movement. Initially the pixel values of all the three channels are null. When any motion is detected at a particular pixel for the first time, then it is represented using MHIR. However, if a repetitive action is performed, then it is represented using MHIG and if overwriting action is thereafter continued for the second time, then MHIB is utilized. In this approach, the pixel intensities are varied in accordance with the basic MHI. Thus, using our methodology which uses multiple channels, MHI is not only capable of detecting the history of motion but is also made capable of representing overlapping repetitive actions.
AB - Motion History Images(MHI) are extensively being used to represent the history of temporal changes involved in the execution of an activity. Here the intensity of the pixels of a scalar valued image are varied, depending upon the motion history. MHI suffers from a very prominent drawback that when self-occluding or over-writing activities are encountered it fails to generate a vivid description of the course of that activity. This happens because when repetitive activities are performed, the current action overwrites or deletes the information of the previous action. In this paper, we have designed a methodology which has overcome this problem of conventional MHI. In our mechanism, we have used red, green and blue channels to represent human movement. Initially the pixel values of all the three channels are null. When any motion is detected at a particular pixel for the first time, then it is represented using MHIR. However, if a repetitive action is performed, then it is represented using MHIG and if overwriting action is thereafter continued for the second time, then MHIB is utilized. In this approach, the pixel intensities are varied in accordance with the basic MHI. Thus, using our methodology which uses multiple channels, MHI is not only capable of detecting the history of motion but is also made capable of representing overlapping repetitive actions.
UR - http://www.scopus.com/inward/record.url?scp=84883413362&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84883413362&partnerID=8YFLogxK
U2 - 10.1109/iccsp.2013.6577116
DO - 10.1109/iccsp.2013.6577116
M3 - Conference contribution
AN - SCOPUS:84883413362
SN - 9781467348669
SP - 556
EP - 560
BT - International Conference on Communication and Signal Processing, ICCSP 2013 - Proceedings
ER -