Region-of-interest based video coding strategy for rate/energy-constrained smart surveillance systems using WMSNs

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

doi:10.1016/j.adhoc.2022.103076

Cited by 15 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AMS [18] utilized a remote server for model training and updated the edge device to improve performance. A. Aliouat et al dug into the video coding strategy and proposed a fast ROI detection method [19].…”

Section: B Video Analytics Optimizationmentioning

confidence: 99%

Edge Computing Resource Management for Cross-Camera Video Analytics: Workload and Model Adaptation

Chen,

Chiang,

Wei

2024

IEEE Access

View full text Add to dashboard Cite

Multi-camera systems are now widely employed across numerous domains. The exponential growth of deep learning has simplified the implementation of advanced video analytics applications. While current systems strive to enhance live video analytics from several aspects, they overlook the potential degradation in performance resulting from dynamic content changes, such as the variation in the quantity and types of objects of interest over a period and across different cameras. The authors introduce Workload and Model Adaptation (WMA), a two-stage resource allocation strategy for a three-tiered, cross-camera video analytics system. This system not only supports model fine-tuning but also ensures workload balance. Notably, both the system architecture and control workflow fully comply with the IEEE 1935 edge standard. This paper delves into the GPU utilization performance of a vehicle re-identification application and examines the workload dynamics spanning multiple cameras. Furthermore, the challenges related to multi-process execution are explored. The system is evaluated using a commonly employed dataset and a popular opensource project. The results demonstrate that the proposed design surpasses the baseline and enhances the overall throughput and latency across cameras within the system.

show abstract

Section: B Video Analytics Optimizationmentioning

confidence: 99%

Edge Computing Resource Management for Cross-Camera Video Analytics: Workload and Model Adaptation

Chen,

Chiang,

Wei

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This is accomplished by managing the bit allocation mechanisms, as shown in [47]. The authors in [32] have provided a more accurate and energy-efficient strategy, in which a good trade-off between energy efficiency, image quality, content awareness, bitrate, and effective machinebased monitoring tasks at the destination have been reached. The strategy seeks to create a new pre-processing method, named Successive Sum of Absolute Differences (S-SAD), to identify the ROI and divide it into many classes based on their importance.…”

Section: Background and Related Workmentioning

confidence: 99%

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

et al. 2023

View full text Add to dashboard Cite

Following its use in several applications, including video coding in wireless surveillance, moving object detection (MOD) has become a popular video analysis topic. Despite the considerable progress in the accuracy of MOD for video coding, its implementation in constrained sensors is a real challenge owing to their high complexity and energy consumption. Therefore, there is a great need to address the trade-off between the accuracy and the energy efficiency of MOD approaches for video coding in constrained systems. In this work, an energy-efficient region-of-interest (ROI) detection algorithm as a pre-encoder for wireless visual surveillance (WVS) is proposed. The algorithm ensures a trade-off between detection accuracy and computational complexity. To this end, we propose constructing an activity map by measuring each block activity between successive frames. The map scores are processed using a combination of a fast Gaussian smoother and a rank-order filter to improve accuracy. Only the blocks in motion are coded and counted for transmission. The accuracy of our approach has been evaluated on a large dataset using key performance metrics. It has been found that our algorithm outperforms other state-of-theart techniques in terms of true positive rate (TPR), with 80.84% on sensitivity metric, while exhibiting a well-balanced accuracy for all categories. A careful examination of the computational complexity confirms the low overhead. The energy and bitrate savings could achieve nearly 90% and 98%, respectively.

show abstract

“…The proposed QPC-SV technique's innovative design principles hold promise for diverse video types and potential incorporation into future video coding standards. Aliouat et al [26] introduced an energy-efficient video coding strategy with a fast region-of-interest (ROI) detection method. The lightweight ROI detection method divides frames into four regions, and the coding strategy extracts two classes of ROI for coding and transmission at variable quality levels based on relevance.…”

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

Region-of-interest based video coding strategy for rate/energy-constrained smart surveillance systems using WMSNs

Cited by 15 publications

References 34 publications

Edge Computing Resource Management for Cross-Camera Video Analytics: Workload and Model Adaptation

Edge Computing Resource Management for Cross-Camera Video Analytics: Workload and Model Adaptation

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

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

Contact Info

Product

Resources

About