Maximum projection and velocity estimation algorithm for small moving target detection in space surveillance

Yao, Dalei; Wen, Desheng; Xue, Jianru; Chen, Zhi; Wen, Yue; Jiang, Baotan; Ma, Junyong

doi:10.1117/12.2202360

Cited by 5 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use qualitative and quantitative analysis to show the performance of our algorithm. We use a variety of target detection methods for comparison, including: MHT algorithm (Blostein & Huang 1991), NTH algorithm (Bai & Zhou 2010), IMVP algorithm (Yao & Wen 2015), HSS algorithm (Du et al 2016), 1DSE algorithm (Wei et al 2018) and our proposed algorithm. Figure 13 shows the comparison image of the target detection effect of various algorithms, we build the precisionrecall curve shown in Figure 14, and comprehensive evaluation through quantitative and qualitative.…”

Section: Space Debris Detectionmentioning

confidence: 99%

“…Therefore, the algorithm is not applicable in some situations (Kravchonok 2011). Yao et al proposed a target detection method based on the maximum projection method, which uses the time index and the target centroid to estimate the target motion speed (Yao et al 2015). Li et al use a multi-level hypothesis testing algorithm, which uses hypothesis testing to remove unverified trajectories to achieve the purpose of reducing the amount.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Space Debris Extraction Channel Based on Large Field of view Photoelectric Detection System

Jiang¹,

Liu²,

Yang³

et al. 2022

PASP

View full text Add to dashboard Cite

Space target detection is the core technology of space surveillance system. The large field of view telescope has strong space detection capabilities, and its realization also faces many challenges. We propose an automatic extraction algorithm for space debris, aiming to automatically extract information about space targets. Our method is mainly divided into three parts. In the first stage, image denoising processing is carried out for various noise interference in the image. The proposed wavelet transform and total variational hybrid filtering algorithm are applied to eliminate noise, which reduces the impact of noise on target detection and greatly retains target information. In the second stage, we propose an improved morphological operator to eliminate uneven background. The third stage uses Hough transform to obtain candidate debris targets. These images were taken during an observation campaign, the observatory is located in Jilin. Experimental results show that the target detection algorithm proposed in this paper can effectively extract space target information and solve the problem of space target detection for large-field telescopes.

show abstract

Section: Space Debris Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic Space Debris Extraction Channel Based on Large Field of view Photoelectric Detection System

Jiang¹,

Liu²,

Yang³

et al. 2022

PASP

View full text Add to dashboard Cite

show abstract

“…However, for targets with unknown speeds, the performance of the algorithm decreases. In 2015, Yao et al, " [28] proposed a space target detection and velocity estimation method based on the maximum projection method. These space target detection algorithms mentioned are not based on deep learning, and many of them use artificially designed target features to achieve single target detection.…”

Section: Related Workmentioning

confidence: 99%

STAR-24K: A Public Dataset for Space Common Target Detection

2022

KSII TIIS

View full text Add to dashboard Cite

The target detection algorithm based on supervised learning is the current mainstream algorithm for target detection. A high-quality dataset is the prerequisite for the target detection algorithm to obtain good detection performance. The larger the number and quality of the dataset, the stronger the generalization ability of the model, that is, the dataset determines the upper limit of the model learning. The convolutional neural network optimizes the network parameters in a strong supervision method. The error is calculated by comparing the predicted frame with the manually labeled real frame, and then the error is passed into the network for continuous optimization. Strongly supervised learning mainly relies on a large number of images as models for continuous learning, so the number and quality of images directly affect the results of learning. This paper proposes a dataset STAR-24K (meaning a dataset for Space TArget Recognition with more than 24,000 images) for detecting common targets in space. Since there is currently no publicly available dataset for space target detection, we extracted some pictures from a series of channels such as pictures and videos released by the official websites of NASA (National Aeronautics and Space Administration) and ESA (The European Space Agency) and expanded them to 24,451 pictures. We evaluate popular object detection algorithms to build a benchmark. Our STAR-24K dataset is publicly available at https://github.com/Zzz-zcy/STAR-24K.

show abstract

Space target detection in optical image sequences for wide-field surveillance

Liu

Wang

et al. 2020

International Journal of Remote Sensing

View full text Add to dashboard Cite

Maximum projection and velocity estimation algorithm for small moving target detection in space surveillance

Cited by 5 publications

References 7 publications

Automatic Space Debris Extraction Channel Based on Large Field of view Photoelectric Detection System

Automatic Space Debris Extraction Channel Based on Large Field of view Photoelectric Detection System

STAR-24K: A Public Dataset for Space Common Target Detection

Space target detection in optical image sequences for wide-field surveillance

Contact Info

Product

Resources

About