Multi-Threshold-Based Frame Segmentation for Content-Aware Video Coding in WMSN

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

doi:10.1007/978-3-031-12097-8_29

Cited by 2 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [16], the authors proposed an ED-based ROI detection technique using the Sobel edge detector to extract the edges of the moving regions and create an activity map based on those detected edges. While in [30], the Canny ED is used as a low-cost edge detection method to extract the ROI prior to compression. ROI detection has also been a solution to control the memory usage [45], the bitrate [46], and the quality of the video encoder.…”

Section: Background and Related Workmentioning

confidence: 99%

“…Figure (7) illustrates the per-frame energy consumption of the proposed method compared to ROI-based compression methods, namely, [30] referred to as EMP '22, [16] referred to as SSD'22 and the forward baseline compression (MJPEG). Since the algorithm is applied to each frame, constant energy is spent for each frame, while the total energy curves oscillate based on the number of blocks to compress.…”

Section: ) Energy Dissipation For Complete Compression Chainmentioning

confidence: 99%

“…Despite the good ROI detection of the other techniques, they are weakened by the high energy cost in the detection step. This is due to the adopted edge detection and automatic thresholding techniques in [30] [16] respectively. Those techniques are computationally extensive due to the use of arithmetic convolution and histogram calculation.…”

Section: ) Energy Dissipation For Complete Compression Chainmentioning

confidence: 99%

See 2 more Smart Citations

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