Embedded deep vision in smart cameras for multi-view objects representation and retrieval. (July 2017)

• Record Type: Journal Article
• Authors: Ahmad, Jamil; Mehmood, Irfan; Rho, Seungmin; Chilamkurti, Naveen; Baik, Sung Wook
• Is Part Of: Computers & electrical engineering. Volume 61(2017)
• Page Start: 297
• Page End: 311
• Publication Date: 2017-07
• Subjects: Embedded processing -- Convolutional neural network -- Transfer learning -- Image retrieval; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2017.05.033
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Efficient convolutional neural network based feature extraction framework for embedded vision. Surveillance object representation with compact deep features. Multi-view queries for improved retrieval performance in surveillance datasets. Abstract: Active large scale surveillance of indoor and outdoor environments with multiple cameras is becoming an undeniable necessity in today's connected world. Enhanced computational and storage capabilities in smart cameras establish them as promising platforms for implementing intelligent and autonomous surveillance networks. However, poor resolution, limited number of samples per object, and pose variation in multi-view surveillance streams, make the task of efficient image representation highly challenging. To address these issues, we propose an efficient and powerful convolutional neural network (CNN) based framework for features extraction using embedded processing on smart cameras. Efficient, high performance, pre-trained CNNs are separately fine-tuned on persons and vehicles to obtain discriminative, low dimensional features from segmented surveillance objects. Furthermore, multi-view queries of surveillance objects are used to improve retrieval performance. Experiments reveal better efficiency and retrieval performance in different surveillance datasets. Graphical abstract: