Earth Observation Satellite Learning to Video Compressor complexity reduction

Bayat, Mohammadreza; Liu, Rongke; Arman, Ladan; Zarrini, Hossein

doi:10.1109/aero47225.2020.9172789

Cited by 5 publications

(3 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarities are omitted, and motion estimated vectors and the difference residue between the primary and estimated blocks are sent. The decoder reconstructs the frame with minimal error by implementing this algorithm in reverse [2].…”

Section: Satellites Design Compatible With Video Compression Techniquesmentioning

confidence: 99%

Utilizing Motion Direction of Video Capturing Satellites for Complexity Reduction in Video Compressor Block-Matching Techniques

Bayat,

Rongke,

Zarrini

2024

Preprint

Self Cite

View full text Add to dashboard Cite

This paper aims to define how to combine satellite motion direction in Video Compressor Block-Matching algorithms. In this study, three objectives were identified: unveiling the existence of the problem by evidence-gathering, proposing a preliminary satellite design for video-capturing missions, and using the motion pattern of a satellite. To satisfy the first research objective, videos of Earth and other celestial bodies were selected, and the validity of this claim was evaluated. The alignment of the direction of satellite motion with the motion vectors can be clearly recognized. In all cases, except for one case, the motion vectors of the selected videos were shown to be more than 80%. Investigations determined that the review of the divisions of the Regions and appropriate selection of the boundaries of the Regions can produce more acceptable results for the video whose dominated motion vectors are divided into two different Regions. To satisfy the second objective, which is defined as creating the necessary changes in the design of satellites that have the mission of capturing videos of the celestial bodies, a conceptual design was presented in which the path of receiving the motion directions from the satellite platform to the payload was specified. Here, two modes were proposed: Normal and Proposed. In future rounds, this information can be used to reduce the amount of motion estimation calculations and complexity.

show abstract

Section: Satellites Design Compatible With Video Compression Techniquesmentioning

confidence: 99%

Utilizing Motion Direction of Video Capturing Satellites for Complexity Reduction in Video Compressor Block-Matching Techniques

Bayat,

Rongke,

Zarrini

2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Targeting RGB and multispectral on-board video compression, a tailored version of commercial video encoder widely used on ground applications, such as the H.264/AVC specification [6], could be adapted to work on-board satellites, as it is recommended by the space agencies for real-time applications with data transmissions up to 25 Mb/s [7]. Although this option offers good performance in terms of compression ratedistortion ratio, it also presents coarse drawbacks in order to be implemented on hardware, such as a complex architecture (specially the inter-prediction stage, where motion estimation is computed), preventing its implementation on hardware resources available on-board satellites [8], or an imprecise behaviour for lossless compression, among others. Different works are available in the state-of-the-art about FPGA implementations of the H.264 encoder, but focusing in particular stages whose performance is critical, such as motion estimation [9], [10], [11], [12], the intra-prediction [13], [14], quantization [15] or the encoding [16], [17].…”

Section: Introductionmentioning

confidence: 99%

Adaptation of the CCSDS 123.0-B-2 Standard for RGB Video Compression

Barrios

Guerra

López

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The integration of video sensors on-board satellites is becoming a trend in the space industry, since they provide extra information in the temporal domain when compared with traditional remote sensing imaging acquisition equipment. The inclusion of the temporal dimension together with the constant increase of the sensor resolution supposes a challenge for onboard processing, taking into account the limited computational and storage resources on-board satellites and that it is unfeasible to directly transmit raw video to ground, due to downlink bandwidth limitations. For these reasons, on-board video compression is needed. However, the inherent complexity of the video encoders used on ground limits their implementation on environments with high constraints in terms of computational burden, area and power consumption. This work proposes an extended compression chain that implements as compression core the CCSDS-123.0-B-2 standard, originally developed for near-lossless compression of multi-and hyperspectral images. In addition, some preprocessing stages are included to manage the temporal dimension of RGB video efficiently. The proposed solution guarantees low complexity and flexibility to compress both multi-and hyperspectral images, and panchromatic and RGB video by using a single compression instance, which is adapted by adding or removing the appropriate stages. Results demonstrate the viability of this solution to be implemented on space payloads, since high compression ratios are achieved without incurring in a penalty in terms of video quality.

show abstract

“…A series of video satellites have been deployed in recent years. e video satellite can obtain the submeter resolution color dynamic video through the staring imaging mode and obtain continuous video image data of the area of interest, which is particularly suitable for regional dynamic change monitoring, such as situation changes, dynamic target reconnaissance and surveillance, and attack effect evaluation [1][2][3][4]. At the same time, it can also meet various civil needs such as antiterrorism, disaster prevention and relief, and intelligent traffic control.…”

Section: Introductionmentioning

confidence: 99%

Multitarget Detection and Tracking Method in Remote Sensing Satellite Video

Lei

Guo

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

A remote sensing video satellite multiple object detection and tracking method based on road masking, Gaussian mixture model (GMM), and data association is proposed. This method first extracts the road network from the remote sensing video based on deep learning. In the detection stage, the background subtraction algorithm is used based on the GMM to obtain the detection results of the moving targets on the road. In the tracking stage, the data association of the same target detection result in adjacent frames is realized based on the neighborhood search algorithm, so as to obtain the continuous tracking trajectory of each target. The experiments about multiobject detection and tracking are conducted on data measure by real remote sensing satellites, and the results verified the feasibility of the proposed method.

show abstract

Earth Observation Satellite Learning to Video Compressor complexity reduction

Cited by 5 publications

References 47 publications

Utilizing Motion Direction of Video Capturing Satellites for Complexity Reduction in Video Compressor Block-Matching Techniques

Utilizing Motion Direction of Video Capturing Satellites for Complexity Reduction in Video Compressor Block-Matching Techniques

Adaptation of the CCSDS 123.0-B-2 Standard for RGB Video Compression

Multitarget Detection and Tracking Method in Remote Sensing Satellite Video

Contact Info

Product

Resources

About