An Efficient Low Complexity Region-of-Interest Detection for Video Coding in Wireless Visual Surveillance

Aliouat, Ahcen; Kouadria, Nasreddine; Harize, Saliha; Maimour, Moufida

doi:10.1109/access.2023.3248067

Cited by 8 publications

(3 citation statements)

References 58 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…UVCNet capitalizes on surveillance video characteristics and achieves state-of-the-art results on three widely used surveillance video datasets. In an article Aliouat et al [29] proposed an energy-efficient region-of-interest (ROI) detection algorithm for wireless visual surveillance (WVS). The algorithm measures activity between successive frames to construct an activity map, using a Gaussian smoother and rank-order filter to improve accuracy, and transmits only the motion blocks.…”

Section: Best Match Block After 2nd Iterationmentioning

confidence: 99%

Object Detection driven Composite Block MotionEstimation Algorithm for High-FidelitySurveillance Video Coding

Pal,

Biswas,

Jichkar

et al. 2023

Preprint

View full text Add to dashboard Cite

The accurate estimation of motion in video sequences is a critical task in various computer vision applications, such as video compression, video surveillance, and autonomous navigation. Block matching is a popular method for motion estimation that involves finding the best match between blocks of pixels in consecutive frames. However, using a single block matching algorithm for the entire frame may not be efficient, especially when dealing with dynamic scenes containing moving objects. In this paper, we propose a novel approach for motion estimation using composite block matching algorithms based on object detection. Our method first detects the moving objects in the video frame using a deep learningbased object detection algorithm. Then, we use one block matching algorithm for the area of the frame where the objects are detected, and another block matching algorithm for the remaining part of the frame. The rationale behind using two different algorithms is that the area containing the objects usually has more complex motion patterns and may require a more sophisticated and rigorous algorithm than the rest of the frame. Our results show that the proposed method achieves higher accuracy and faster processing time compared to any single motion estimation methods. The composite block matching algorithm provides more accurate motion estimation in the object regions, leading to better object tracking and less motion artifacts. Moreover, the use of a simpler block matching algorithm for the non-object regions reduces computational overhead, making the overall process more efficient for compression surveillance video.

show abstract

Section: Best Match Block After 2nd Iterationmentioning

confidence: 99%

Object Detection driven Composite Block MotionEstimation Algorithm for High-FidelitySurveillance Video Coding

Pal,

Biswas,

Jichkar

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The DoF level is high if the object is faraway from focal-length. Defocus-blur detection is used in numerous computer vision applications, such as focused object detection [1], background blur magnification [2], image refocusing [3], depth estimation [4,5], image information security [6], text detection [7], partial image deblurring [8,9] and efficient-energy based region-of-interest detection in wireless visual surveillance and video coding method [55,56].…”

Section: Introductionmentioning

confidence: 99%

A Novel Defocus-Blur Region Detection Approach Based on DCT Feature and PCNN Structure

Basar,

Ali,

Waheed

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The motion or out-of-focus effect in digital images is the main reason for the blurred regions in defocused-blurred images. It may adversely affect various image features such as texture, pixel, and region. Therefore, it is important to detect in-focused objects in defocused-blurred images after the segmentation of blurred and non-blurred regions. The state-of-the-art techniques are prone to noisy pixels, and their local descriptors for developing segmentation metrics are also complex. To address these issues, this research, therefore, proposed a novel and hybrid focused detection approach based on Discrete Cosine Transform (DCT) coefficients and PC Neural Net (PCNN) structure. The proposed approach partially resolves the limitations of the existing contrast schemes to detect focused smooth objects from the outof-focused smooth regions in the defocus dataset. The visual and quantitative evaluation illustrates that the proposed approach outperformed in terms of accuracy and efficiency to referenced algorithms. The highest ℱ 𝛼 -score of the proposed approach on Zhao's dataset is 0.7940 whereas on Shi's dataset is 0.9178.

show abstract

“…Among the recent critical tasks in computer vision, semantic segmentation is one of those important tasks. It is employed in robotics [4], 3D image understanding [5], medical diagnosis [6], Virtual/Augmented reality [7], Video coding (Region-of-interest coding) [8], [9], and self-driving vehicles [10]. Thus performing this task in real-time is extremely beneficial for those applications.…”

mentioning

confidence: 99%

SDDS-Net: Space and Depth Encoder-Decoder Convolutional Neural Networks for Real-Time Semantic Segmentation

Ibrahem,

Salem,

Kang

2023

IEEE Access

View full text Add to dashboard Cite

In this paper, we propose novel convolutional encoder-decoder architectures for real-time semantic segmentation based on an image-to-image translation approach via the space-to-depth and depth-tospace modules. We present architectures that compress the spatial information of the image using the spaceto-depth (SD) instead of the commonly used pooling methods (Max-pooling and Average-pooling) or strided convolution approaches. The SD module can reduce the image size while preserving the spatial information of the image in the form of extra depth information, this approach is much better than the pooling approaches which introduce a loss in the information and the details of the image. We also propose a lightweight and simple decoder stage using the depth-to-space (DS) module which constructs a high-resolution dense prediction map from a large number of low-resolution feature maps. The proposed architectures are efficient in learning image classification and semantic segmentation with high accuracy and average processing speed. We trained and tested our proposed architectures on image classification (i.e. CIFAR10 and Tiny ImageNet), and indoor and outdoor benchmarks for semantic segmentation specifically NYU-depthV2 and CITYSCAPES. The proposed architectures could attain high accuracy in classification (94.28% on CIFAR10 and 72.25% on Tiny ImageNet) and high mean average precision and pixel accuracy values in semantic segmentation (pixel accuracy of 78.55% on NYU-depthV2 and 87.9% on CITYSCAPES) while maintaining a real-time speed of frame processing outperforming recent state-of-the-art methods in semantic segmentation.

show abstract

An Efficient Low Complexity Region-of-Interest Detection for Video Coding in Wireless Visual Surveillance

Cited by 8 publications

References 58 publications

Object Detection driven Composite Block MotionEstimation Algorithm for High-FidelitySurveillance Video Coding

Object Detection driven Composite Block MotionEstimation Algorithm for High-FidelitySurveillance Video Coding

A Novel Defocus-Blur Region Detection Approach Based on DCT Feature and PCNN Structure

SDDS-Net: Space and Depth Encoder-Decoder Convolutional Neural Networks for Real-Time Semantic Segmentation

Contact Info

Product

Resources

About