Tracking error detection method for novel multi-level discs

Bacterial colonies detecting and counting is tedious and time-consuming work. Fortunately CNN (convolutional neural network) detection methods are effective for target detection. The bacterial colonies are a kind of small targets, which have been a difficult problem in the field of target detection technology. This paper proposes a small target enhancement detection method based on double CNNs, which can not only improve the detection accuracy, but also maintain the detection speed similar to the general detection model. The detection method uses double CNNs. The first CNN uses SSD_MOBILENET_V1 network with both target positioning and target recognition functions. The candidate targets are screened out with a low confidence threshold, which can ensure no missing detection of small targets. The second CNN obtains candidate target regions according to the first round of detection, intercepts image sub-blocks one by one, uses the MOBILENET_V1 network to filter out targets with a higher confidence threshold, which can ensure good detection of small targets. Through the two-round enhancement detection method has been transplanted to the embedded platform NVIDIA Jetson AGX Xavier, the detection accuracy of small targets is significantly improved, and the target error detection rate and missed detection rate are reduced to less than 1%.

Download Full-text

Saliency Contour Extraction Based on Multi-level Feature Channel Optimization Coding

Electronics Science Technology and Application ◽

10.18686/esta.v7i4.168 ◽

2021 ◽

Vol 7 (4) ◽

pp. 117

Author(s):

Linling Fang ◽

Yingle Fan

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Network Model ◽

Detection Method ◽

Gabor Filter ◽

Contour Detection ◽

Frequency Separation ◽

Experimental Sample ◽

Multi Level ◽

End To End

<p>A biomimetic vision computing model based on multi-level feature channel optimization coding is proposed and applied to image contour detection, combining the end-to-end detection method of full convolutional neural network and the traditional contour detection method based on biological vision mechanism. Considering the effectiveness of the Gabor filter in perceiving the scale and direction of the image target, the Gabor filter is introduced to simulate the multi-level feature response on the visual path. The optimal scale and direction of the Gabor filter are obtained based on the similarity index, and they are used as the frequency separation parameter of the NSCT transform. The contour sub-image obtained by the NSCT transform is combined with the original image for feature enhancement and fusion to realize the primary contour response. The low-dimensional and low-redundancy primary contour response is used as the input sample of the network model to relieve network pressure and reduce computational complexity. A fully improved convolutional neural network model is constructed for multi-scale training, through feature encoder to feature decoder, to achieve end-to-end pixel prediction, and obtain a complete and continuous detection image of the subject contour. Using the BSDS500 atlas as the experimental sample, the average accuracy index is 0.85, which runs on the device CPU at a detection rate of 20+ FPS to achieve a good balance between training efficiency and detection effect.</p>

Download Full-text

RESILIENT FLOCKING CONTROL FOR CONNECTED AND AUTOMATED VEHICLES WITH CYBER-ATTACK THREATS

ASME Letters in Dynamic Systems and Control ◽

10.1115/1.4050123 ◽

2021 ◽

pp. 1-7

Author(s):

Fengchen Wang ◽

Yan Chen

Keyword(s):

Detection Method ◽

Tracking Error ◽

Attack Detection ◽

Cyber Attacks ◽

Vehicle Tracking ◽

Cyber Attack ◽

Dynamics Model ◽

Automated Vehicles ◽

Tracking Errors ◽

Error Dynamics

Abstract To improve the cybersecurity of flocking control for connected and automated vehicles (CAVs), this paper proposes a novel resilient flocking control by specifically considering cyber-attack threats on vehicle tracking errors. Using the vehicle tracking error dynamics model, a dual extended Kalman filter (DEKF) is applied to detect cyber-attacks as an unknown constant on vehicle tracking information with noise rejections. To handle the coupling effects between tracking errors and cyber-attacks, the proposed DEKF consists of a tracking error filter and a cyber-attack filter, which are utilized to conduct the prediction and correction of tracking errors alternatively. Whenever an abnormal tracking error is detected, an observer-based resilient flocking control is enabled. Demonstrated by simulation results, the proposed cyber-attack detection method and resilient flocking control design can successfully achieve and maintain the flocking control of multi-CAV systems by rejecting certain cyber-attack threats.

Download Full-text

Alignment error detection method of sub-eye mounting hole for bionic compound eye system

Chinese Optics ◽

10.3788/co.20191204.0880 ◽

2019 ◽

Vol 12 (4) ◽

pp. 880-887

Author(s):

张广 ZHANG Guang ◽

王新华 WANG Xin-hua ◽

李大禹 LI Da-yu

Keyword(s):

Error Detection ◽

Compound Eye ◽

Detection Method ◽

Alignment Error

Download Full-text

The Fault Detection Method of CAN Bus Based on Network Resistance Model

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.58-60.1948 ◽

2011 ◽

Vol 58-60 ◽

pp. 1948-1952

Author(s):

Chuan Qiang Yu ◽

Zhen Dong Qi ◽

Zhen Ye Wang ◽

Yu Wang

Keyword(s):

Fault Detection ◽

Error Detection ◽

Data Exchange ◽

Detection Method ◽

Can Bus ◽

High Reliability ◽

Detection Mechanism ◽

Network Bandwidth ◽

Resistance Model ◽

Bus Network

In the error detection mechanism of CAN bus, when the failed node or line is not in the data exchange path, you will not detect the fault, in order to solve this problem, a method is proposed which is realized by adding an external hardware detection circuit in the CAN-bus network, the fault will be detected through testing the resistance of the CAN bus network. In this paper, the network resistance model of CAN bus is established, and the principle of network resistance fault detection method is analyzed. We have carried out several experiments by the network with three nodes to test the validity of this method. As the results of our experiments, we concluded that the method can real-time and comprehensively detect the fault of network and do not take up the network bandwidth, so this method can effectively resolve the problems of current detection mechanism and have good application prospect in some high reliability requirements occasions.

Download Full-text

A Novel Vehicle Detection Method Based on the Fusion of Radio Received Signal Strength and Geomagnetism

Sensors ◽

10.3390/s19010058 ◽

2018 ◽

Vol 19 (1) ◽

pp. 58 ◽

Cited By ~ 4

Author(s):

Liangliang Lou ◽

Jinyi Zhang ◽

Yong Xiong ◽

Yanliang Jin

Keyword(s):

Error Detection ◽

Detection Method ◽

Signal Strength ◽

Vehicle Detection ◽

Received Signal Strength ◽

Detection Accuracy ◽

Detection Problem ◽

Traffic Light ◽

Radio Stations ◽

Multiple Detection

A geomagnetic signal blind zone exists between the front and rear axle of high-chassis vehicle such as trucks and buses, which leads to multiple-detection problem in detecting those vehicles running at low speed on roads or error-detection problem in the case of the stopping position of the vehicle is not standard when waiting for the traffic light to change. In order to improve the detection accuracy of any type of vehicle running at any speed, a novel two-sensors data fusion vehicle detection method through combining received signal strength from radio stations with geomagnetism around vehicles is designed and verified in the paper. Experimental results show that the accuracy of our proposed method can reach 95.4% and traditional single magnetism-based detection method was only 83.4% in the detection of high-chassis vehicles.

Download Full-text

The Assembly Error Detection of Automotive Airbag Based on Machine Vision

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.738-739.694 ◽

2015 ◽

Vol 738-739 ◽

pp. 694-698

Author(s):

Xiao Dong Wang ◽

Qi Liu ◽

Wei Zhang

Keyword(s):

Machine Vision ◽

Error Detection ◽

Template Matching ◽

Assembly Line ◽

Detection Method ◽

Ccd Camera ◽

Processing Method ◽

Canny Edge Detection ◽

Canny Edge ◽

Assembly Error

Based on the principle of machine vision technology, we designed a methodto detect the outline dimensions of automotive airbag quickly and accurately. We Used CCD camera obtain the airbag image, through the image processing method ofsmooth filtering andgray-scale transformationto complete pre-processing, finally applied Canny edge detection operator to extract the boundary of the airbag contour features,and then took the template matching methodto detect assemble error of the airbag image whether meet the requirement.The results show that the detection method have a higher precision, and the time is very short, it can improve the sampled positioningerror detection for the all checks image recognition detection, suitable for application in real-time online detection of airbag assembly line.

Download Full-text