Robustness Study of a Deep Convolutional Neural Network for Vehicle Detection in Aerial Imagery

Ilina, O. V.; Терешонок, М. В.

doi:10.1134/s1064226922020048

Cited by 8 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Support vector machines are based on statistical theory, and support vector machines are often used in machine learning in the case of small samples. e support vector machine uses the optimization method to obtain the global optimal solution, which can effectively avoid local optimization and overlearning [11][12][13], and can be applied to regression and classification problems. Least squares support vector machine evaluation principle is as follows: set a training sample set to be described by s � {x i , y i }, where i � 1, 2, .…”

Section: Evaluation Principle Of Least Squares Support Vectormentioning

confidence: 99%

An Intelligent Assessment Method of English Teaching Ability Based on Improved Machine Learning Algorithm

Narengerile

2022

Security and Communication Networks

View full text Add to dashboard Cite

In order to fully exploit the effect of intelligent evaluation of English teaching ability and explore the quality of English teaching, an intelligent evaluation method of English teaching ability based on improved machine learning algorithm is proposed, which can ensure the rational allocation of English teaching resources, analyze the big data of constraint parameters of English teaching ability evaluation, and obtain frequent item sets of English teaching quality based on big data mining technology. The particle swarm optimization (PSO) method was used to improve the parameters of the SVM, and the optimal parameters of the support vector machines (SVM) were obtained, which were input into the sample of English teaching effect evaluation, and a method was constructed to maximize the SVM. The optimal parameters are introduced into the decision function, so as to achieve the purpose of English teaching quality assessment. The experimental results show that the proposed method has a high convergence speed and can achieve rapid convergence with only 30 network trainings. At the same time, the evaluation accuracy of English teaching quality is as high as 95%, the correlation coefficient of the results is as high as 0.95, and the evaluation time is low. It is less than 150 ms, and the keyword frequency identification is better and better, which can realize the objective evaluation of online teaching quality.

show abstract

Section: Evaluation Principle Of Least Squares Support Vectormentioning

confidence: 99%

An Intelligent Assessment Method of English Teaching Ability Based on Improved Machine Learning Algorithm

Narengerile

2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…(4) IoU cost: (17) where B ∩ B GT represents the intersection between the predicted and ground-truth boxes, and B ∪ B GT represents their union.…”

Section: Scylla-intersection Over Unionmentioning

confidence: 99%

“…It is more difficult to detect than typical smoke that has already taken shape and is susceptible to disturbances, such as lens impurities. This leads to the problem of UAVs obtaining noisy images during detection missions, which can cause missed detections [17] as well as false detections caused by interfering objects, such as cloud cover [18]. These make the detection of forest smoke a major challenge.…”

Section: Introductionmentioning

confidence: 99%

LMDFS: A Lightweight Model for Detecting Forest Fire Smoke in UAV Images Based on YOLOv7

Chen,

Cheng,

Lin

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Forest fires pose significant hazards to ecological environments and economic society. The detection of forest fire smoke can provide crucial information for the suppression of early fires. Previous detection models based on deep learning have been limited in detecting small smoke and smoke with smoke-like interference. In this paper, we propose a lightweight model for forest fire smoke detection that is suitable for UAVs. Firstly, a smoke dataset is created from a combination of forest smoke photos obtained through web crawling and enhanced photos generated by using the method of synthesizing smoke. Secondly, the GSELAN and GSSPPFCSPC modules are built based on Ghost Shuffle Convolution (GSConv), which efficiently reduces the number of parameters in the model and accelerates its convergence speed. Next, to address the problem of indistinguishable feature boundaries between clouds and smoke, we integrate coordinate attention (CA) into the YOLO feature extraction network to strengthen the extraction of smoke features and attenuate the background information. Additionally, we use Content-Aware Reassembly of FEatures (CARAFE) upsampling to expand the receptive field in the feature fusion network and fully exploit the semantic information. Finally, we adopt SCYLLA-Intersection over Union (SIoU) loss as a replacement for the original loss function in the prediction phase. This substitution leads to improved convergence efficiency and faster convergence. The experimental results demonstrate that the LMDFS model proposed for smoke detection achieves an accuracy of 80.2% with a 5.9% improvement compared to the baseline and a high number of Frames Per Second (FPS)—63.4. The model also reduces the parameter count by 14% and Giga FLoating-point Operations Per second (GFLOPs) by 6%. These results suggest that the proposed model can achieve a high accuracy while requiring fewer computational resources, making it a promising approach for practical deployment in applications for detecting smoke.

show abstract

“…Recently, convolutional neural network (CNN) based deep learning methods have been widely applied to vehicle detection 9 – 11 Generally, these methods can be subdivided into two categories. The first category is the region proposal-based CNN method, which generates candidate box images and then feeds them into the detection network for classification and localization.…”

Section: Introductionmentioning

confidence: 99%

ComS-YOLO: a combinational and sparse network for detecting vehicles in aerial thermal infrared images

Zhang,

2024

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Vehicle detection using aerial thermal infrared images has received significant attention because of its strong capability for day and night observations to supply information for vehicle tracking, traffic monitoring, and road network planning. Compared with aerial visible images, aerial thermal infrared images are not sensitive to lighting conditions. However, they have low contrast and blurred edges. Therefore, a combinational and sparse you-only-look-once (ComS-YOLO) neural network is put forward to accurately and quickly detect vehicles in aerial thermal infrared images. Therein, we adjust the structure of the deep neural network to balance the detection accuracy and running time. In addition, we propose an objective function that utilizes the diagonal distance of the corresponding minimum external rectangle, which prevents non-convergence when there is an inclusion relationship between the prediction and true boxes or in the case of width and height alignment. Furthermore, to avoid over-fitting in the training stage, we eliminate some redundant parameters via constraints and on-line pruning. Finally, experimental results on the NWPU VHR-10 and DARPA VIVID datasets show that the proposed ComS-YOLO network effectively and efficiently identifies the vehicles with a low missed rate and false detection rate. Compared with the Faster R-CNN and a series of YOLO neural networks, the proposed neural network presents satisfactory and competitive results in terms of the detection accuracy and running time. Furthermore, vehicle detection experiments under different environments are also carried out, which shows that our method can achieve an excellent and desired performance on detection accuracy and robustness of vehicle detection.

show abstract

Robustness Study of a Deep Convolutional Neural Network for Vehicle Detection in Aerial Imagery

Cited by 8 publications

References 18 publications

An Intelligent Assessment Method of English Teaching Ability Based on Improved Machine Learning Algorithm

An Intelligent Assessment Method of English Teaching Ability Based on Improved Machine Learning Algorithm

LMDFS: A Lightweight Model for Detecting Forest Fire Smoke in UAV Images Based on YOLOv7

ComS-YOLO: a combinational and sparse network for detecting vehicles in aerial thermal infrared images

Contact Info

Product

Resources

About