摘要
In an increasing number of area inspection applications,such as powerline inspection and sewage disposal monitoring,Unmanned Aerial Vehicles(UAVs)are used for capturing and transmitting on-site videos.Existing UAV video compressions employ Advanced Video Coding(AVC)or High Efficiency Video Coding(HEvC)encoders to eliminate intra-frame and short-term inter-frame redundancy,while these methods still face challenges in achieving high compression efficiency due to the high captured video bitrate and limited transmission capacity.In this paper,we further consider that UAVs revisit the same area and capture videos from different viewpoints,hence the Long-term Historical Background Redundancy(LHBR)exists among revisited video clips.Thus,we leverage the LHBR caused by UAV revisits,and propose a high-efficiency aerial video compression for UAVs.Our method comprises three steps:Firstly,we propose a lightweight method based on a spatial correlation model to select the most correlated reference frames from historical video database.Then,we design a Historical Reference Background Frame(HBRF)generation algorithm by alternately using the keypoint-based and telemetry-assisted alignments to align the selected frames with current frame.Finally,we use the generated HBRF as a reference frame to eliminate the LHBR within I-frames.Our proposed method has been experimentally proven to reduce Bjøntegaard-Delta bitrate(BD-bitrate)by 42.83%or enhance Bjøntegaard-Delta Peak Signal-to-Noise Ratio(BD-PSNR)by 2.98 dB over original HEVC,and take 29.3%of the encoding time needed for existing LHBR based compressions.
基金
supported by the National Natural Science Foundation of China(No.62025110).
