<p>We present a novel energy-efficient scheme for the wireless transmission of streaming video data from Internet of Video Things (IoVT) visual sensors to the backhaul network. Our solution employs a dynamic reference frame selection mechanism powered by a Long Short-Term Memory (LSTM) deep learning model to implement a low-complexity, lossless video data encoding scheme. By exploiting temporal correlations in video frames of the JPEG and JPEG 2000 standards, our dynamic reference frame selection mechanism creates a lossless encoding of the video data by eliminating redundant information. The encoded data is further compressed using the Redundant Binary Number System (RBNS), resulting in a non-uniform distribution of symbols, with 0’s being the most frequent occurring symbol. A silent-symbol transmission strategy is employed to transmit the resulting RBNS-encoded data, transmitting only the non-zero RBNS symbols (1 and <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11334_2025_616_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="10" /> </InlineMediaObject> <EquationSource Format="TEX">$\bar{1}$</EquationSource> <EquationSource Format="MATHML"><math> <mover accent="true"> <mrow> <mn>1</mn> </mrow> <mrow> <mo stretchy="false">¯</mo> </mrow> </mover> </math></EquationSource> </InlineEquation>), resulting in significant energy savings. Simulation results on real-world traffic surveillance datasets demonstrate transmitter-side energy savings of over <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11334_2025_616_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="31" /> </InlineMediaObject> <EquationSource Format="TEX">$84\%$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>84</mn> <mo>%</mo> </mrow> </math></EquationSource> </InlineEquation> (for outdoor scenarios) and <InlineEquation ID="IEq3"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11334_2025_616_Article_IEq3.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="31" /> </InlineMediaObject> <EquationSource Format="TEX">$86\%$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>86</mn> <mo>%</mo> </mrow> </math></EquationSource> </InlineEquation> (for indoor scenarios) compared to transmitting raw video files. The proposed method ensures lossless data communication with zero Mean Squared Error (MSE). It outperforms the popular encoding techniques based on neighborhood correlation sequence (NCS) method, discrete wavelet transform (DWT), Haar discrete wavelet transform, high efficiency video coding (HEVC) and AV1 in terms of overall energy efficiency, making it highly suitable for energy-constrained IoVT applications.</p>

Deep learning aided energy-efficient lossless video data transmission from IoVT visual sensors

期刊论文
发表日期：

2025年9月8日

查看全文

Pratham Majumder,
Bhabani P. Sinha,
Koushik Sinha

摘要

We present a novel energy-efficient scheme for the wireless transmission of streaming video data from Internet of Video Things (IoVT) visual sensors to the backhaul network. Our solution employs a dynamic reference frame selection mechanism powered by a Long Short-Term Memory (LSTM) deep learning model to implement a low-complexity, lossless video data encoding scheme. By exploiting temporal correlations in video frames of the JPEG and JPEG 2000 standards, our dynamic reference frame selection mechanism creates a lossless encoding of the video data by eliminating redundant information. The encoded data is further compressed using the Redundant Binary Number System (RBNS), resulting in a non-uniform distribution of symbols, with 0’s being the most frequent occurring symbol. A silent-symbol transmission strategy is employed to transmit the resulting RBNS-encoded data, transmitting only the non-zero RBNS symbols (1 and $\bar{1}$ $\bar{1}$ ), resulting in significant energy savings. Simulation results on real-world traffic surveillance datasets demonstrate transmitter-side energy savings of over $84\%$ $84 %$ (for outdoor scenarios) and $86\%$ $86 %$ (for indoor scenarios) compared to transmitting raw video files. The proposed method ensures lossless data communication with zero Mean Squared Error (MSE). It outperforms the popular encoding techniques based on neighborhood correlation sequence (NCS) method, discrete wavelet transform (DWT), Haar discrete wavelet transform, high efficiency video coding (HEVC) and AV1 in terms of overall energy efficiency, making it highly suitable for energy-constrained IoVT applications.