https://journals.scholarpublishing.org/index.php/AIVP/issue/feed Advances in Image and Video Processing 2019-09-08T08:27:39+00:00 Thomas Harvey aivp@scholarpublishing.org Open Journal Systems <p>Advances in Image and Video Processing is peer-reviewed open access online journal that provides a medium of the rapid publication of original research papers, review articles, book reviews and short communications covering all aspects of image processing and computer vision from the low-level, iconic processes of early vision to the high-level, symbolic processes of recognition and interpretation.</p> https://journals.scholarpublishing.org/index.php/AIVP/article/view/6702 Moving Object Tracking Based on Camshift Algorithm 2019-09-08T08:27:39+00:00 Md Shaiful Islam Babu mdshaifulislambabu@yahoo.com <p>Continuously adaptive Camshift is an efficient and lightweight tracking algorithm developed based on mean-shift. Camshift algorithm has the advantage of better real-time, but this algorithm is only suitable for tracking targets in simple cases, not well for tracking desired targets in complex situation. In this paper, we will present an improved method of multiple targets tracking algorithm based on the Camshift algorithm combined with Kalman filter. The tracker of the improved method was used to track each detected target. It can achieve tracking of multiple targets. A large number of experiments have proved that this algorithm has strong target recognition ability, good anti-noise performance, and fast-tracking speed.</p> 2019-09-08T08:22:55+00:00 Copyright (c) 2019 Advances in Image and Video Processing https://journals.scholarpublishing.org/index.php/AIVP/article/view/6644 Encrypted Color Image Transmission in LQ-based GSIC Pre-coded Multiuser Downlink Wireless Communication System 2019-09-08T08:27:39+00:00 MD OMOR FARUK omor.apee91@gmail.com Shaikh Enayet Ullah enayet_apee@ru.ac.bd <p>The use of LQ-Based GSIC pre-coding scheme in next generation cellular mobile network can be a robust and effective technique for unique cancellation of multiuser interference. In 5G/beyond 5G a great emphasis is being given on ensuring physical layer security. In this paper, an investigative study has been made on the performance evaluation of encrypted color image transmission in LQ-based GSIC pre-coded multiuser downlink wireless communication system. The 6×2 multi-antenna configured simulated system under investigation incorporates SPC (3, 2) channel coding, low order digital modulations (QAM, QPSK, DQPSK), DNA and sine map based RGB image encryption and Zero Forcing (ZF) signal detection techniques. In the scenario of encrypted multiuser color image transmission over AWGN and Rayleigh fading channels, it is observable that the simulative system is very much effective and robust in retrieving color image for each of the three users under a moderate signal to noise ratio of 10 dB.</p> 2019-09-08T08:21:36+00:00 Copyright (c) 2019 Advances in Image and Video Processing https://journals.scholarpublishing.org/index.php/AIVP/article/view/6717 A Framework: Region-Frame-Attention-Compact Bilinear Pooling Layer Based S2VT For Video Description 2019-09-08T08:27:39+00:00 Haifeng Sang jianglia_0119@qq.com Ge Hai jianglia_0119@qq.com <p>In the video description task, the temporal information and visual information of the video are very important for video understanding, and high-level semantic information contained in mixed features of text features and video features plays an important role in the generation of video caption.In order to generate accurate and appropriate video captions.Based on the S2VT (sequence to sequence: video to text)framework, we propose a video description neural network framework (RFAC-S2VT) with a two-level attention and compact linear pooling layer (CBP) fusion.We use visual information and category information from the dataset for class training, and then we use CNN to extract the trained visual features.In the encodering stage,this paper designs a regional attention mechanism to dynamically focus on each frame of video,and then the region-weighted 2D visual features and C3D visual features containing temporal information are then fused together. We use the characteristic of model to model the fusion visual features with temporal information.In the decodering stage, this paper designs a frame-level attention ,and then fine-grained the video features which has been focusd by frame-level attention and the text features in the dataset by using compact linear pooling layer (CBP),finally model generated relevant video caption.We validate the proposed network framework on the MSR-VTT dataset,the results show that our proposed neural network framework is competitive on this dataset and current state of the art.</p> 2019-09-08T08:24:15+00:00 Copyright (c) 2019 Advances in Image and Video Processing