Convolutional Gating Network for Object Tracking

Abstract

A B S T R A C TObject tracking through multiple cameras is a popular research topic in security and surveillance systems especially when human objects are the target. However, occlusion is one of the challenging problems for the tracking process. T his paper proposes a multiple-camera-based cooperative tracking method to overcome the occlusion problem. The paper presents a new model for combining convolutional neural networks (CNNs), which allows the proposed method to learn the features with high discriminative power and geometrical independence. In the training phase, the CNNs are first pre-trained in each of the camera views, and a convolutional gating network (CGN) is simultaneously pre-trained to produce a weight for each CNN output. The CNNs are then transferred to the tracking task where the pre-trained parameters of the CNNs are re-trained by using the data from the tracking phase. T he weights obtained from the CGN are used in order to fuse the features learnt by the CNNs and the resulting weighted combination of the features is employed to represent the objects. Finally, the p article filter is used in order to track objects. The experimental results showed the efficiency of the proposed method in this paper.

Deep Convolutional Neural Network for Finger-Knuckle-Print Recognition

“…Attia et al [25] LeCun and Bengio [27] were the first to propose CNN architecture. CNN models have been the subject of considerable attention in most computer vision applications [28][29][30][31]. These families of neural networks, which combine feature extraction and classification roles, are intended to recognize images based on their scale, shift, and distortions.…”

Human Action Recognition using Prominent Camera

“…Holte et al [16] again used HMC along with 3D Motion Context (3D-MC) as the motion descriptor. Few authors, Feizi [17] and Sezavar et al [18] have implemented Convolution Neural Network (CNN) for their methodologies, but Support Vector Machine (SVM) seems to be the better choice since the main focus is to reduce the computation time and cost [19]. Approaches based on 3D methods are found to be superior to approach based on 2D methods concerning recognition accuracy [20].…”

Routing Protocols for IOT Applications based on Distributed Learning

“…Additionally, utilizing knowledge-based cognition approaches for discovering future changes, a fusion contextual learning model was generated for behavioral knowledge detection. Besides, modeling was provided for collecting data from various sensors in the AmI system in a single meaningful context [13,17].…”

“…Appropriate allocation of restricted resources is achieved using the Figure 1. The architecture of the RPL routing domain distributed method concerning the IoT tools' Quality of Service (QoS) needs [13]. These tools should have the capability to separately obtain their communication resources as supposing their regular communication with the root node is not practical, given their severe resource constraints.…”