Infrared small target detection based on divergence operator and nonlinear classifier

Ma, Tianlei; Wang, Jiaqi; Yang, Zhongguo; Ren, Xiangyang; Song, Yifan; Ku, Yanan; Liu, Yunpeng; Wang, Dongshu

doi:10.1007/s11082-021-03041-4

Cited by 5 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The test results showed that the determined coefficient R 2 of the constructed pine wilt nematode ridge regression model was 0.8686, the mean square error RMSE was 0.2735, and the average estimation accuracy was 87.15%, which provides technical support for the early monitoring and control of pine wilt nematode disease. The method of combining Fast R-CNN and UAV remote sensing proposed by Huang Huayi et al [11] has an accuracy rate of 90%. For UAV image data, Song Yining et al [12] used a linear spectral clustering superpixel algorithm to monitor and locate diseased trees and used support vector machines to accurately locate diseased trees.…”

Section: Introductionmentioning

confidence: 99%

Detection of Pine Wilt Nematode from Drone Images Using UAV

Sun

Ibrayim

Hamdulla

2022

Sensors

View full text Add to dashboard Cite

Pine wilt nematode disease is a devastating forest disease that spreads rapidly. Using drone remote sensing to monitor pine wilt nematode trees promptly is an effective way to control the spread of pine wilt nematode disease. In this study, the YOLOv4 algorithm was used to automatically identify abnormally discolored wilt from pine wilt nematode disease on UAV remote sensing images. Because the network structure of YOLOv4 is too complex, although the detection accuracy is high, the detection speed is relatively low. To solve this problem, the lightweight deep learning network MobileNetv2 is used to optimize the backbone feature extraction network. Furthermore, the YOLOv4 algorithm was improved by improving the backbone network part, adding CBAM attention, and adding the Inceptionv2 structure to reduce the number of model parameters and improve the accuracy and efficiency of identification. The speed and accuracy of the Faster R-CNN, YOLOv4, SSD, YOLOv5, and the improved MobileNetv2-YOLOv4 algorithm were compared, and the detection effects of the Faster R-CNN, YOLOv4, SSD, YOLOv5 and the improved MobileNetv2-YOLOv4 algorithm on trees with pine wilt nematode were analyzed. The experimental results show that the average precision of the improved MobileNetv2-YOLOv4 algorithm is 86.85%, the training time of each iteration cycle is 156 s, the parameter size is 39.23 MB, and the test time of a single image is 15 ms, which is better than Faster R-CNN, YOLOv4, and SSD, but comparable to YOLOv5. Compared with the advantages and disadvantages, comprehensively comparing these four indicators, the improved algorithm has a more balanced performance in the detection speed, the parameter size, and the average precision. The F1 score of the improved algorithm (95.60%) was higher than that of Faster R-CNN (90.80%), YOLOv4 (94.56%), and SSD (92.14%), which met the monitoring requirements of pine wilt nematode trees. Faster R-CNN and SSD pine-wilt-nematode tree detection models are not ideal in practical applications. Compared with the YOLOv4 pine-wilt-nematode tree detection model, the improved MobileNetv2-YOLOv4 algorithm satisfies the condition of maintaining a lower model parameter quantity to obtain higher detection accuracy; therefore, it is more suitable for practical application scenarios of embedded devices. It can be used for the rapid detection of pine wilt nematode diseased trees.

show abstract

Section: Introductionmentioning

confidence: 99%

Detection of Pine Wilt Nematode from Drone Images Using UAV

Sun

Ibrayim

Hamdulla

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…When evaluating the ability of space-based detection systems to detect targets, the signal-to-clutter ratio (SCR) and signal-to-noise ratio (SNR) are commonly used as the evaluation index. (Huang, F. et al 2012;Zhang, W. et al 2021;Hu, Z. et al 2019;Zavvari, M. et al 2015;Ma, T. et al 2021) Caroline, S. used SCR as a criterion to analyze the detectability of missiles in different infrared bands and discussed the impact of different observation scenes and spatial resolution on SCR (Schweitzer, C. et al 2012). Yuan, H. calculated the local SCR at the aircraft plume position in three bands to analyze the detectability under the sea/cloud background from space-based platform Yuan, H. et al 2020).…”

Section: Introductionmentioning

confidence: 99%

A novel detection performance modular evaluation metric of space-based infrared system

Zhou

Zhang

et al. 2022

Opt Quant Electron

View full text Add to dashboard Cite

In order to reflect the space-based full chain information of the detection process comprehensively and objectively, we proposed a novel modular evaluation metric to discuss the target, background and system independently. It takes the equivalent radiation intensity as the parameter, which can evaluate the detection performance of the system quantitatively. In this paper, taking the fifth-generation American stealth fighter F22 as an example, the mathematical detection model of the space-based infrared system to aircraft targets in the Earth background is described. A modular evaluation metric is proposed. The simulation analyzes the impact of different detection scenes and system parameters on system equivalent irradiance. Furthermore, recommendations for the optimization of the detection system are given. The research results provide a new idea for the analysis of the detection performance of highly maneuverable targets under dynamic backgrounds and have guiding significance for the performance evaluation and parameter design of the infrared detection system.

show abstract

“…A non-subsampled contourlet transform model combined with SVD was proposed in [9] to adjust coefficients through singular values to make the infrared target protuberant. Different from them, local contrast-based methods [10][11][12][13][14][15] use the brightness differences of the target and neighboring areas to detect small targets. Chen et.…”

Section: Introductionmentioning

confidence: 99%

Mask-guided infrared small multi-target detection via coarse-to-fine candidate selection

Zhang

Lin

et al. 2022

Opt Quant Electron

View full text Add to dashboard Cite

Infrared acquisition technology is often used for target detection in military fields, since it is not easily disturbed by diverse environmental factors. However, the characteristics of low image contrast, coupled with complex imaging backgrounds, long distance and the lack of visual features, making infrared small targets detection a challenging task. The generic deep neural network-based models are struggled to be applied for infrared small targets, since the increased network layers may lead to the gradually loss of target features and positional information. To address above issues, we propose a mask-guided detection model via the coarseto-fine candidate selection for infrared small multi-target detection. More specifically, to enhance target features and guide the localization process in the neural network, we propose to utilize the foreground mask generated by referring to the non-local self-correlation property of infrared background and the sparse property of target distribution. The obtained mask is treated as the prior to re-weight the convolutional feature maps. Considering the complex background, the multi-target detection is prone to mis-detections. Therefore, we propose a coarse-to-fine candidate selection method on top of the initial detection results. A shallow network is constructed to extract more nuanced visual features from the candidate positions for a binary classification, in which the false positive candidates are ruled out free from the disruptions of other background features. Moreover, given the lack of multi-target infrared datasets, we propose two synthetic datasets based on the public available and own collected infrared data. Extensive experimental results verify the effectiveness and advantages of our model compared to state-of-the-art methods.

show abstract

Infrared small target detection based on divergence operator and nonlinear classifier

Cited by 5 publications

References 40 publications

Detection of Pine Wilt Nematode from Drone Images Using UAV

Detection of Pine Wilt Nematode from Drone Images Using UAV

A novel detection performance modular evaluation metric of space-based infrared system

Mask-guided infrared small multi-target detection via coarse-to-fine candidate selection

Contact Info

Product

Resources

About