Low-altitude infrared small target detection based on fully convolutional regression network and graph matching

Wang, Huaichao; Li, Haifeng; Zhou, Huidi; Chen, Xinwei

doi:10.1016/j.infrared.2021.103738

Cited by 20 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the STSM can help us locate the target well, it still needs to excavate more information to confirm the final detection results. Inspired by pipeline filter [ 5 ] and graph matching [ 43 ], we design an LTC measure to eliminate random clutters and registration error by utilizing the global trajectory continuity feature further.…”

Section: Methodsmentioning

confidence: 99%

Low-Altitude Infrared Slow-Moving Small Target Detection via Spatial-Temporal Features Measure

Rao

Chen

et al. 2022

Sensors

View full text Add to dashboard Cite

Robust detection of infrared slow-moving small targets is crucial in infrared search and tracking (IRST) applications such as infrared guidance and low-altitude security; however, existing methods easily cause missed detection and false alarms when detecting infrared small targets in complex low-altitude scenes. In this article, a new low-altitude slow-moving small target detection algorithm based on spatial-temporal features measure (STFM) is proposed. First, we construct a circular kernel to calculate the local grayscale difference (LGD) in a single image, which is essential to suppress low-frequency background and irregular edges in the spatial domain. Then, a short-term energy aggregation (SEA) mechanism with the accumulation of the moving target energy in multiple successive frames is proposed to enhance the dim target. Next, the spatial-temporal saliency map (STSM) is obtained by integrating the two above operations, and the candidate targets are segmented using an adaptive threshold mechanism from STSM. Finally, a long-term trajectory continuity (LTC) measurement is designed to confirm the real target and further eliminate false alarms. The SEA and LTC modules exploit the local inconsistency and the trajectory continuity of the moving small target in the temporal domain, respectively. Experimental results on six infrared image sequences containing different low-altitude scenes demonstrate the effectiveness of the proposed method, which performs better than the existing state-of-the-art methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Low-Altitude Infrared Slow-Moving Small Target Detection via Spatial-Temporal Features Measure

Rao

Chen

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The two assumptions of the optical flow method are that the brightness between adjacent frames is constant and that the small motion of the moving object between adjacent frames cannot be too large [3,4,6] . Suppose is the gray value of the point in the star image at time t. After the time dt changes, the moving distance of the pixel in the star image is .…”

Section: Optical Flow Methodsmentioning

confidence: 99%

“…The dilating can be represented by , which can be expressed as follows: (6) where denotes the image to be processed after correlation filtering and is the domain of definition of , stands for the structure operator at the point and is the domain of definition of . Considering that the stars are circular patches of light in the star chart, the structure elements are selected with a radius greater than the radius of the star.…”

Section: Star Image Preprocessingmentioning

confidence: 99%

A star extraction method of dynamic star image for low signal-to-noise ratio based on joint probability estimation of optical flow-trajectory

Han

Sun

Li³

et al. 2022

Optical Design and Testing XII

View full text Add to dashboard Cite

The star sensor is an attitude-sensitive device for spaceflight. It is a critical component in the autonomous attitude determination of aerospace vehicles. Compared to other attitude sensors, the star sensor offers higher attitude accuracy, low power consumption, small volume, and strong autonomy. It plays an important role in high-precision remote sensing, astronomical navigation, and other fields. Star extraction is an essential part of the star sensor in the process of working. Its accuracy and the number of extracted stars affect the performance of the star sensor. This paper proposes a method of star extraction based on the combination of the Improved Optical Flow Method (IOFM) and Dynamic Filtering (DF) named IOFM-DF. Based on the optical flow method, the motion characteristics of stars in the time and space domains are considered. Due to the difference between the star and noise in the motion trajectory, dynamic filtering is used to reduce the influence of noise from the star image on the extraction effect of the star. Considering the statistical properties of the motion trajectories of multiple stars, the cosine distance of the motion track between the extracted point and the star is calculated to predict the probability that the extracted point belongs to the star. IOFM-DF can extract and track stars in the star image for a low signal-to-noise ratio. Experimental results show that IOFM-DF increases the number of star extractions by at least 30% compared to traditional methods. This research is important to improve the accuracy and performance of star sensors.

show abstract

“…Deep-learning-based methods, such as SSD [19], Faster R-CNN [23], YOLO [22], U-Net [24], and so on, achieved excellent results in visible light object detection and segmentation. In order to deal with ISTD, many technologies has been proposed, including model pruning [36,8,30], multi-scale fusion [34,10,16], multi-modal fusion [25,29,26], feature pyramid [27,35,15], etc. ACM [5] and ALC-Net [6] utilized a top-down global attention module and a bottom-up local attention module to separately transfer semantic information and context information, and to prevent the disappearance of small targets.…”

Section: Related Workmentioning

confidence: 99%

“…When using deep convolution neural networks (DC-NNs) for target detection, such a small target is easy to disappear because the feature resolution is gradually reduced in forward propagation [6,5]. Most of the existing methods simplify DCNNs designed for visible light target detection to alleviate the problem of small targets disappearing [36,8,30], but this simplification will bring another problem of insufficient expressive capacity [14].…”

Section: Introductionmentioning

confidence: 99%

CourtNet for Infrared Small-Target Detection

Peng¹,

Zhao²,

Hu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Infrared small-target detection (ISTD) is an important computer vision task. ISTD aims at separating small targets from complex background clutter. The infrared radiation decays over distances, making the targets highly dim and prone to confusion with the background clutter, which makes the detector challenging to balance the precision and recall rate. To deal with this difficulty, this paper proposes a neuralnetwork-based ISTD method called CourtNet, which has three sub-networks: the prosecution network is designed for improving the recall rate; the defendant network is devoted to increasing the precision rate; the jury network weights their results to adaptively balance the precision and recall rate. Furthermore, the prosecution network utilizes a densely connected transformer structure, which can prevent small targets from disappearing in the network forward propagation. In addition, a fine-grained attention module is adopted to accurately locate the small targets. Experimental results show that CourtNet achieves the best F1-score on the two ISTD datasets, MFIRST (0.62) and SIRST (0.73).

show abstract

Low-altitude infrared small target detection based on fully convolutional regression network and graph matching

Cited by 20 publications

References 25 publications

Low-Altitude Infrared Slow-Moving Small Target Detection via Spatial-Temporal Features Measure

Low-Altitude Infrared Slow-Moving Small Target Detection via Spatial-Temporal Features Measure

A star extraction method of dynamic star image for low signal-to-noise ratio based on joint probability estimation of optical flow-trajectory

CourtNet for Infrared Small-Target Detection

Contact Info

Product

Resources

About