Diseases Detection of Occlusion and Overlapping Tomato Leaves Based on Deep Learning

Background: In view of the existence of light shadow, branches occlusion, and leaves overlapping conditions in the real natural environment, problems such as slow detection speed, low detection accuracy, high missed detection rate, and poor robustness in plant diseases and pests detection technology arise.Results: Based on YOLOv3-tiny network architecture, to reduce layer-by-layer loss of information during network transmission, and to learn from the idea of inverse-residual block, this study proposes a YOLOv3-tiny-IRB algorithm to optimize its feature extraction network, improve the gradient disappearance phenomenon during network deepening, avoid feature information loss, and realize network multilayer feature multiplexing and fusion. The network is trained by the methods of expanding datasets and multiscale strategies to obtain the optimal weight model.Conclusion: The experimental results show that when the method is tested on the self-built tomato diseases and pests dataset, and while ensuring the detection speed (206 frame rate per second), the mean Average precision (mAP) under three conditions: (a) deep separation, (b) debris occlusion, and (c) leaves overlapping are 98.3, 92.1, and 90.2%, respectively. Compared with the current mainstream object detection methods, the proposed method improves the detection accuracy of tomato diseases and pests under conditions of occlusion and overlapping in real natural environment.

Download Full-text

Implementation of the PointPillars Network for 3D Object Detection in Reprogrammable Heterogeneous Devices Using FINN

Journal of Signal Processing Systems ◽

10.1007/s11265-021-01733-4 ◽

2021 ◽

Author(s):

Joanna Stanisz ◽

Konrad Lis ◽

Marek Gorgon

Keyword(s):

Object Detection ◽

Network Architecture ◽

Point Cloud ◽

Hardware Implementation ◽

Frame Rate ◽

Detection Accuracy ◽

Embedded Platform ◽

Heterogeneous Devices ◽

Fundamental Causes ◽

3D Object Detection

AbstractIn this paper, we present a hardware-software implementation of a deep neural network for object detection based on a point cloud obtained by a LiDAR sensor. The PointPillars network was used in the research, as it is a reasonable compromise between detection accuracy and calculation complexity. The Brevitas / PyTorch tools were used for network quantisation (described in our previous paper) and the FINN tool for hardware implementation in the reprogrammable Zynq UltraScale+ MPSoC device. The obtained results show that quite a significant computation precision limitation along with a few network architecture simplifications allows the solution to be implemented on a heterogeneous embedded platform with maximum 19% AP loss in 3D, maximum 8% AP loss in BEV and execution time 375ms (the FPGA part takes 262ms). We have also compared our solution in terms of inference speed with a Vitis AI implementation proposed by Xilinx (19 Hz frame rate). Especially, we have thoroughly investigated the fundamental causes of differences in the frame rate of both solutions. The code is available at https://github.com/vision-agh/pp-finn.

Download Full-text

A New Method for Detecting Compensation Hole Parameters of Automobile Brake Master Cylinder Based on Machine Vision

Journal of Advanced Transportation ◽

10.1155/2021/8864679 ◽

2021 ◽

Vol 2021 ◽

pp. 1-14

Author(s):

Changfu Zhao ◽

Hongchang Ding ◽

Guohua Cao ◽

Ying Zhang

Keyword(s):

Hough Transform ◽

New Method ◽

Zernike Moment ◽

Machining Accuracy ◽

Detection Accuracy ◽

Master Cylinder ◽

Fast Detection ◽

Detection Technology ◽

Center Position ◽

Detection Speed

The machining accuracy of the compensation hole of the automobile brake master cylinder directly determines the safety of the automobile and the reliability of parking. How to detect the parameters of the compensation hole with high precision becomes a crucial issue. In this paper, by analyzing the principle of Hough transform detection technology and several optimization algorithms, a new method combining Zernike moment and improved gradient Hough transform is proposed to detect the circular hole parameters. The simulation experiment shows that the proposed algorithm satisfies 0.1 pixels in the coordinate detection of the center position, and the radius detection accuracy is 0.05 pixels, with fast detection speed and good robustness. Compared with the random Hough transform algorithm and the gradient Hough transform algorithm, the algorithm proposed in this paper has higher detection accuracy, faster detection speed, and better robustness, which meets the online detection accuracy requirements of the brake master cylinder compensation hole.

Download Full-text

End-to-End Ship Detection in SAR Images for Complex Scenes Based on Deep CNNs

Journal of Sensors ◽

10.1155/2021/8893182 ◽

2021 ◽

Vol 2021 ◽

pp. 1-19

Author(s):

Yao Chen ◽

Tao Duan ◽

Changyuan Wang ◽

Yuanyuan Zhang ◽

Mo Huang

Keyword(s):

Data Augmentation ◽

Feature Fusion ◽

Detection Methods ◽

Detection Accuracy ◽

Deep Convolutional Neural Networks ◽

Sar Images ◽

Ship Detection ◽

End To End ◽

Sar Imagery ◽

Detection Speed

Ship detection on synthetic aperture radar (SAR) imagery has many valuable applications for both civil and military fields and has received extraordinary attention in recent years. The traditional detection methods are insensitive to multiscale ships and usually time-consuming, results in low detection accuracy and limitation for real-time processing. To balance the accuracy and speed, an end-to-end ship detection method for complex inshore and offshore scenes based on deep convolutional neural networks (CNNs) is proposed in this paper. First, the SAR images are divided into different grids, and the anchor boxes are predefined based on the responsible grids for dense ship prediction. Then, Darknet-53 with residual units is adopted as a backbone to extract features, and a top-down pyramid structure is added for multiscale feature fusion with concatenation. By this means, abundant hierarchical features containing both spatial and semantic information are extracted. Meanwhile, the strategies such as soft non-maximum suppression (Soft-NMS), mix-up and mosaic data augmentation, multiscale training, and hybrid optimization are used for performance enhancement. Besides, the model is trained from scratch to avoid learning objective bias of pretraining. The proposed one-stage method adopts end-to-end inference by a single network, so the detection speed can be guaranteed due to the concise paradigm. Extensive experiments are performed on the public SAR ship detection dataset (SSDD), and the results show that the method can detect both inshore and offshore ships with higher accuracy than other mainstream methods, yielding the accuracy with an average of 95.52%, and the detection speed is quite fast with about 72 frames per second (FPS). The actual Sentinel-1 and Gaofen-3 data are utilized for verification, and the detection results also show the effectiveness and robustness of the method.

Download Full-text

Lightweight Detection Network Based on Sub-Pixel Convolution and Objectness-Aware Structure for UAV Images

Sensors ◽

10.3390/s21165656 ◽

2021 ◽

Vol 21 (16) ◽

pp. 5656

Author(s):

Xuanye Li ◽

Hongguang Li ◽

Yalong Jiang ◽

Meng Wang

Keyword(s):

Object Detection ◽

Computational Cost ◽

Frame Rate ◽

Detection Methods ◽

Detection Accuracy ◽

Small Object ◽

Mobile Platforms ◽

Efficient Detection ◽

Uav Images ◽

Uav Image

Unmanned Aerial Vehicles (UAVs) can serve as an ideal mobile platform in various situations. Real-time object detection with on-board apparatus provides drones with increased flexibility as well as a higher intelligence level. In order to achieve good detection results in UAV images with complex ground scenes, small object size and high object density, most of the previous work introduced models with higher computational burdens, making deployment on mobile platforms more difficult.This paper puts forward a lightweight object detection framework. Besides being anchor-free, the framework is based on a lightweight backbone and a simultaneous up-sampling and detection module to form a more efficient detection architecture. Meanwhile, we add an objectness branch to assist the multi-class center point prediction, which notably improves the detection accuracy and only takes up very little computing resources. The results of the experiment indicate that the computational cost of this paper is 92.78% lower than the CenterNet with ResNet18 backbone, and the mAP is 2.8 points higher on the Visdrone-2018-VID dataset. A frame rate of about 220 FPS is achieved. Additionally, we perform ablation experiments to check on the validity of each part, and the method we propose is compared with other representative lightweight object detection methods on UAV image datasets.

Download Full-text

Metal Surface Defect Detection Using Modified YOLO

Algorithms ◽

10.3390/a14090257 ◽

2021 ◽

Vol 14 (9) ◽

pp. 257

Author(s):

Yiming Xu ◽

Kai Zhang ◽

Li Wang

Keyword(s):

Neural Network ◽

Metal Surface ◽

Defect Detection ◽

Surface Defect ◽

Detection Methods ◽

Cluster Center ◽

Detection Accuracy ◽

Detection Technology ◽

Speed Advantage ◽

Surface Defect Detection

Aiming at the problems of inefficient detection caused by traditional manual inspection and unclear features in metal surface defect detection, an improved metal surface defect detection technology based on the You Only Look Once (YOLO) model is presented. The shallow features of the 11th layer in the Darknet-53 are combined with the deep features of the neural network to generate a new scale feature layer using the basis of the network structure of YOLOv3. Its goal is to extract more features of small defects. Furthermore, then, K-Means++ is used to reduce the sensitivity to the initial cluster center when analyzing the size information of the anchor box. The optimal anchor box is selected to make the positioning more accurate. The performance of the modified metal surface defect detection technology is compared with other detection methods on the Tianchi dataset. The results show that the average detection accuracy of the modified YOLO model is 75.1%, which ia higher than that of YOLOv3. Furthermore, it also has a great detection speed advantage, compared with faster region-based convolutional neural network (Faster R-CNN) and other detection algorithms. The improved YOLO model can make the highly accurate location information of the small defect target and has strong real-time performance.

Download Full-text

Design and Application of Virtual Instrument Detection System for Aerodynamic Instrument

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.508.166 ◽

2012 ◽

Vol 508 ◽

pp. 166-169

Author(s):

Ping Zhang ◽

Kun Li ◽

Xiao Shu Sun ◽

Xian Wen Gao

Keyword(s):

Virtual Instrument ◽

Control Method ◽

Detection System ◽

Complex Structure ◽

Detection Methods ◽

Detection Accuracy ◽

Fuzzy Pid Control ◽

Output Pressure ◽

Labview Software ◽

Detection Technology

Aerodynamic instruments are widely used in various kinds of industrial equipment, which have many types and complex structure. The traditional instrument detection methods require replacing a variety of testing equipment frequently. Their testing efficiencies are low and the testing equipments are hard to be integrated together. Virtual instrument technology is a hot detection technology in recent years with high detection accuracy and integration, which has a good solution to the problems of traditional detection methods. First of all, this paper introduces an overall design scheme for the virtual detection system. Secondly, for properties of longer response time, overshoot, and difficulties in establishing precise mathematical model of the pneumatic control system, this paper uses fuzzy PID control method to control the pneumatic output pressure. Finally, the virtual detection system is realized based on LabVIEW software platform. This system is applied to the detection of fixed-wing aircraft aerodynamic instrument, and has satisfactory results.

Download Full-text

Hyperspectral Anomaly Detection Based on Separability-Aware Sample Cascade

Remote Sensing ◽

10.3390/rs11212537 ◽

2019 ◽

Vol 11 (21) ◽

pp. 2537 ◽

Cited By ~ 2

Author(s):

Dandan Ma ◽

Yuan Yuan ◽

Qi Wang

Keyword(s):

Anomaly Detection ◽

Large Scale ◽

Hyperspectral Image ◽

Superior Performance ◽

Detection Methods ◽

Background Information ◽

Detection Accuracy ◽

Layer By Layer ◽

Edge Preserving ◽

Image Pixels

A hyperspectral image usually covers a large scale of ground scene, which contains various materials with different spectral properties. When directly exploring the background information using all the image pixels, complex spectral interactions and inter-/intra-difference of different samples will significantly reduce the accuracy of background evaluation and further affect the detection performance. To address this problem, this paper proposes a novel hyperspectral anomaly detection method based on separability-aware sample cascade model. Through identifying separability of hyperspectral pixels, background samples are sifted out layer-by-layer according to their separable degrees from anomalies, which can ensure the accuracy and distinctiveness of background representation. First, as spatial structure is beneficial for recognizing target, a new spectral–spatial feature extraction technique is used in this work based on the PCA technique and edge-preserving filtering. Second, depending on different separability computed by sparse representation, samples are separated into different sets which can effectively and completely reflect various characteristics of background across all the cascade layers. Meanwhile, some potential abnormal targets are removed at each selection step to avoid their effects on subsequent layers. Finally, comprehensively taking different good properties of all the separability-aware layers into consideration, a simple multilayer anomaly detection strategy is adopted to obtain the final detection map. Extensive experimental results on five real-world hyperspectral images demonstrate our method’s superior performance. Compared with seven representative anomaly detection methods, our method improves the average detection accuracy with great advantages.

Download Full-text

The Research on the Detection Methods of EMU Break Valves Features

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.687-691.1034 ◽

2014 ◽

Vol 687-691 ◽

pp. 1034-1037

Author(s):

Chun Ling Guan

Keyword(s):

Neural Network ◽

Feature Detection ◽

Detection Methods ◽

Detection Accuracy ◽

Characteristic Parameters ◽

Spatial Function ◽

Network Algorithm ◽

Detection Technology ◽

Neural Network Algorithm ◽

Multiple Units

This paper focuses on the detection technology for Electric Multiple Units (EMU) break valves features. Aiming at the issues of EMU break valves features detection, this paper propose a kind of EMU break valves feature detection technology based on neural network algorithm which does not overly dependent on break valve characteristic parameters. The spatial function neural network algorithm is used to predict the EMU break valves features. The experiments illustrate the proposed algorithm can increase the detection accuracy with satisfactory effects in EMU break valves features detection.

Download Full-text

Depthwise Separable Convolution Neural Network for High-Speed SAR Ship Detection

Remote Sensing ◽

10.3390/rs11212483 ◽

2019 ◽

Vol 11 (21) ◽

pp. 2483 ◽

Cited By ~ 15

Author(s):

Zhang ◽

Shi ◽

Wei

Keyword(s):

Neural Network ◽

Real Time ◽

Network Architecture ◽

High Speed ◽

Fishery Management ◽

Convolution Neural Network ◽

Detection Accuracy ◽

Ship Detection ◽

Military Planning ◽

Detection Speed

As an active microwave imaging sensor for the high-resolution earth observation, synthetic aperture radar (SAR) has been extensively applied in military, agriculture, geology, ecology, oceanography, etc., due to its prominent advantages of all-weather and all-time working capacity. Especially, in the marine field, SAR can provide numerous high-quality services for fishery management, traffic control, sea-ice monitoring, marine environmental protection, etc. Among them, ship detection in SAR images has attracted more and more attention on account of the urgent requirements of maritime rescue and military strategy formulation. Nowadays, most researches are focusing on improving the ship detection accuracy, while the detection speed is frequently neglected, regardless of traditional feature extraction methods or modern deep learning (DL) methods. However, the high-speed SAR ship detection is of great practical value, because it can provide real-time maritime disaster rescue and emergency military planning. Therefore, in order to address this problem, we proposed a novel high-speed SAR ship detection approach by mainly using depthwise separable convolution neural network (DS-CNN). In this approach, we integrated multi-scale detection mechanism, concatenation mechanism and anchor box mechanism to establish a brand-new light-weight network architecture for the high-speed SAR ship detection. We used DS-CNN, which consists of a depthwise convolution (D-Conv2D) and a pointwise convolution (P-Conv2D), to substitute for the conventional convolution neural network (C-CNN). In this way, the number of network parameters gets obviously decreased, and the ship detection speed gets dramatically improved. We experimented on an open SAR ship detection dataset (SSDD) to validate the correctness and feasibility of the proposed method. To verify the strong migration capacity of our method, we also carried out actual ship detection on a wide-region large-size Sentinel-1 SAR image. Ultimately, under the same hardware platform with NVIDIA RTX2080Ti GPU, the experimental results indicated that the ship detection speed of our proposed method is faster than other methods, meanwhile the detection accuracy is only lightly sacrificed compared with the state-of-art object detectors. Our method has great application value in real-time maritime disaster rescue and emergency military planning.

Download Full-text

A Rapid Recognition Method for Electronic Components Based on the Improved YOLO-V3 Network

Electronics ◽

10.3390/electronics8080825 ◽

2019 ◽

Vol 8 (8) ◽

pp. 825 ◽

Cited By ~ 8

Author(s):

Rui Huang ◽

Jinan Gu ◽

Xiaohong Sun ◽

Yongtao Hou ◽

Saad Uddin

Keyword(s):

Deep Learning ◽

Intelligent Manufacturing ◽

Detection Methods ◽

Detection Accuracy ◽

Electronic Components ◽

Recognition Method ◽

Image Labeling ◽

Fast Recognition ◽

Speed And Accuracy ◽

Detection Speed

Rapid object recognition in the industrial field is the key to intelligent manufacturing. The research on fast recognition methods based on deep learning was the focus of researchers in recent years, but the balance between detection speed and accuracy was not well solved. In this paper, a fast recognition method for electronic components in a complex background is presented. Firstly, we built the image dataset, including image acquisition, image augmentation, and image labeling. Secondly, a fast recognition method based on deep learning was proposed. The balance between detection accuracy and detection speed was solved through the lightweight improvement of YOLO (You Only Look Once)-V3 network model. Finally, the experiment was completed, and the proposed method was compared with several popular detection methods. The results showed that the accuracy reached 95.21% and the speed was 0.0794 s, which proved the superiority of this method for electronic component detection.

Download Full-text