High resolution object detection algorithm based on parallel

Han Gao, Ruiwen Hu, Yixuan Zhao, Tanbao Yan


With the continuous development and improvement of the aviation information warfare system, target detection technology has also become a key part of the airborne system to perceive the environment. Traditional target detection technology is now difficult to meet the requirements of high precision and high real-time performance in airborne scenarios. With the continuous development of deep learning technology, neural network has become the latest method to deal with object detection task, which greatly improves its accuracy and processing efficiency. However, due to the different targets detected in airborne scenes, the scale of data needed to be processed by using neural networks to process target detection tasks also expands dramatically, and the computing resources provided by single chip are already difficult to meet the needs of target detection algorithm execution in airborne environment. This paper proposes a set of high-precision target detection algorithms based on parallelism, which greatly improves the precision and processing efficiency of the target detection algorithm in airborne scenarios.


Object Detection; Data Parallel; Space Parallel; High Resolution Image

Full Text:


Included Database


Alex Krizhevsky, Ilya Sutskever, and Geo.rey E Hinton. 2012. ImageNet Classication with Deep Convolutional Neural Networks[J]. In Advances in Neural Information Processing Systems 25, F. Pereira, C. J. C. Burges, L. Bo.ou, and K. Q.Weinberger(Eds.). Curran Associates, Inc., 1097–1105.

Olga Russakovsky, et al. Imagenet large scale visual recognition challenge[J]. International Journal of Computer Vision, 115(3):211–252, 2015.

Joseph Redmon and Ali Farhadi. 2016. YOLO9000: Be.er, Faster, Stronger[J]. CoRRabs/1612. 08242 (2016).

Adam Van E.en, CosmiQ Works, In-Q-Tel. You Only Look Twice: Rapid Multi-Scale target Detection In Satellite Imagery[J]. 24 May 2018.

V´ıt R°uˇziˇcka and Franz Franchetti,Department of Electrical and Computer Engineering, Carnegie Mellon University. Fast and accurate target detection in high resolution 4K and 8K video using GPUs[J]. 24 Oct 2018.

Radway, R.M., Bartolo, A., Jolly, P.C. et al. Illusion of large on-chip memory by networked computing chips for neural network inference. Nat Electron 4, 71–80 (2021).

DOI: http://dx.doi.org/10.18686/esta.v9i4.299


  • There are currently no refbacks.

Copyright (c) 2023 Han Gao, Ling Xu, Yixuan Zhao, Tanbao Yan

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.