TY - GEN
T1 - Context-aware collaborative object recognition for distributed multi camera time series data
AU - Shin, Philip W.
AU - Sampson, Jack
AU - Narayanan, Vijaykrishnan
N1 - Funding Information:
This work was supported in part by a National Science Foundation(NSF)Award 1317560 and Semiconductor Research Center(SRC) Joint University Microelectronics Program (JUMP) Center for Brain-inspired Computing(C-BRIC)
Publisher Copyright:
© 2019 Association for Computing Machinery.
PY - 2019/12/4
Y1 - 2019/12/4
N2 - Recent research shows that the multi-view system for object recognition outperforms the single-view point system. When viewpoints are added, additional communication cost and cost to deploy the viewpoints are also added. However, prior work has shown that not all of the views are useful, and poor viewpoints can be excluded. This paper explores the dynamic context application for a Context-Aware Neural Network. The Context-Aware Neural Network uses Shannon entropy value to acquire likelihood, and this likelihood value to reduce viewpoints in a distributed system. However, reducing viewpoints were done on static image recognition, so the spatial relation between the views and subject is fixed. Expansion to dynamic context is essential since most of the real world is a series of images, rather than a snapshot of the scene. Apart from testing on images of 3D CAD data, this paper illustrates the generation of 3D CAD data videos, and examines the video analysis of the generated videos using the Context-Aware Neural Network. In this particular setup, relevant objects move with respect to a fixed set of cameras. It is reported that the viewpoints can be reduced, and context of the trained data matters in the setup.
AB - Recent research shows that the multi-view system for object recognition outperforms the single-view point system. When viewpoints are added, additional communication cost and cost to deploy the viewpoints are also added. However, prior work has shown that not all of the views are useful, and poor viewpoints can be excluded. This paper explores the dynamic context application for a Context-Aware Neural Network. The Context-Aware Neural Network uses Shannon entropy value to acquire likelihood, and this likelihood value to reduce viewpoints in a distributed system. However, reducing viewpoints were done on static image recognition, so the spatial relation between the views and subject is fixed. Expansion to dynamic context is essential since most of the real world is a series of images, rather than a snapshot of the scene. Apart from testing on images of 3D CAD data, this paper illustrates the generation of 3D CAD data videos, and examines the video analysis of the generated videos using the Context-Aware Neural Network. In this particular setup, relevant objects move with respect to a fixed set of cameras. It is reported that the viewpoints can be reduced, and context of the trained data matters in the setup.
UR - http://www.scopus.com/inward/record.url?scp=85077819877&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077819877&partnerID=8YFLogxK
U2 - 10.1145/3368926.3369666
DO - 10.1145/3368926.3369666
M3 - Conference contribution
AN - SCOPUS:85077819877
T3 - ACM International Conference Proceeding Series
SP - 154
EP - 161
BT - Proceedings of the 10th International Symposium on Information and Communication Technology, SoICT 2019
PB - Association for Computing Machinery
T2 - 10th International Symposium on Information and Communication Technology, SoICT 2019
Y2 - 4 December 2019 through 6 December 2019
ER -