Real time complex cruise scene detection technology in target recognition

2014 ◽  
Vol 29 (5) ◽  
pp. 844-849
Author(s):  
武治国 WU Zhiguo ◽  
李桂菊 LI Guiju
Keyword(s):  
Real Time ◽  
Target Recognition ◽  
Scene Detection ◽  
Detection Technology

scholarly journals Electroanalytical Biosensors for Circulating Tumor DNA Detection—A Brief Review

2021 ◽  
Author(s):  
Zhijia Peng ◽  
Xiaogang Lin ◽  
Weiqi Nian ◽  
Xiaodong Zheng ◽  
Jayne Wu
Keyword(s):  
Real Time ◽  
Point Of Care ◽  
Low Cost ◽  
High Sensitivity ◽  
High Specificity ◽  
Circulating Tumor Dna ◽  
Minimal Invasive ◽  
Diagnosis And Treatment ◽  
Detection Technology ◽  
Tumor Dna

Early diagnosis and treatment have always been highly desired in the fight against cancer, and detection of circulating tumor DNA (ctDNA) has recently been touted as highly promising for early cancer screening. Consequently, the detection of ctDNA in liquid biopsy gains much attention in the field of tumor diagnosis and treatment, which has also attracted research interest from the industry. However, traditional gene detection technology is difficult to achieve low cost, real-time and portable measurement of ctDNA. Electroanalytical biosensors have many unique advantages such as high sensitivity, high specificity, low cost and good portability. Therefore, this review aims to discuss the latest development of biosensors for minimal-invasive, rapid, and real-time ctDNA detection. Various ctDNA sensors are reviewed with respect to their choices of receptor probes, detection strategies and figures of merit. Aiming at the portable, real-time and non-destructive characteristics of biosensors, we analyze their development in the Internet of Things, point-of-care testing, big data and big health.

scholarly journals Design of a Scalable and Fast YOLO for Edge-Computing Devices

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6779
Author(s):  
Byung-Gil Han ◽  
Joon-Goo Lee ◽  
Kil-Taek Lim ◽  
Doo-Hyun Choi
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Processing Speed ◽  
Edge Computing ◽  
Light Weight ◽  
Detection Technology ◽  
Accuracy Performance ◽  
Speed And Accuracy

With the increase in research cases of the application of a convolutional neural network (CNN)-based object detection technology, studies on the light-weight CNN models that can be performed in real time on the edge-computing devices are also increasing. This paper proposed scalable convolutional blocks that can be easily designed CNN networks of You Only Look Once (YOLO) detector which have the balanced processing speed and accuracy of the target edge-computing devices considering different performances by exchanging the proposed blocks simply. The maximum number of kernels of the convolutional layer was determined through simple but intuitive speed comparison tests for three edge-computing devices to be considered. The scalable convolutional blocks were designed in consideration of the limited maximum number of kernels to detect objects in real time on these edge-computing devices. Three scalable and fast YOLO detectors (SF-YOLO) which designed using the proposed scalable convolutional blocks compared the processing speed and accuracy with several conventional light-weight YOLO detectors on the edge-computing devices. When compared with YOLOv3-tiny, SF-YOLO was seen to be 2 times faster than the previous processing speed but with the same accuracy as YOLOv3-tiny, and also, a 48% improved processing speed than the YOLOv3-tiny-PRN which is the processing speed improvement model. Also, even in the large SF-YOLO model that focuses on the accuracy performance, it achieved a 10% faster processing speed with better accuracy of 40.4% [email protected] in the MS COCO dataset than YOLOv4-tiny model.

scholarly journals Slim and Efficient Neural Network Design for Resource-Constrained SAR Target Recognition

2018 ◽  
Vol 10 (10) ◽  
pp. 1618 ◽  
Author(s):  
Hongyi Chen ◽  
Fan Zhang ◽  
Bo Tang ◽  
Qiang Yin ◽  
Xian Sun
Keyword(s):  
Neural Networks ◽  
Real Time ◽  
Convolutional Neural Networks ◽  
Target Recognition ◽  
Practical Implementation ◽  
Network Storage ◽  
Specific Situation ◽  
Resource Constrained ◽  
Adaptive Architecture ◽  
Deep Cnn

Deep convolutional neural networks (CNN) have been recently applied to synthetic aperture radar (SAR) for automatic target recognition (ATR) and have achieved state-of-the-art results with significantly improved recognition performance. However, the training period of deep CNN is long, and the size of the network is huge, sometimes reaching hundreds of megabytes. These two factors of deep CNN hinders its practical implementation and deployment in real-time SAR platforms that are typically resource-constrained. To address this challenge, this paper presents three strategies of network compression and acceleration to decrease computing and memory resource dependencies while maintaining a competitive accuracy. First, we introduce a new weight-based network pruning and adaptive architecture squeezing method to reduce the network storage and the time of inference and training process, meanwhile maintain a balance between compression ratio and classification accuracy. Then we employ weight quantization and coding to compress the network storage space. Due to the fact that the amount of calculation is mainly reflected in the convolution layer, a fast approach for pruned convolutional layers is proposed to reduce the number of multiplication by exploiting the sparsity in the activation inputs and weights. Experimental results show that the convolutional neural networks for SAR-ATR can be compressed by 40 × without loss of accuracy, and the number of multiplication can be reduced by 15 × . Combining these strategies, we can easily load the network in resource-constrained platforms, speed up the inference process to get the results in real-time or even retrain a more suitable network with new image data in a specific situation.

Detection Accuracy on X-Ray Real Time Imaging for Cast Aluminum Parts

2012 ◽  
Vol 452-453 ◽  
pp. 1513-1517
Author(s):  
Ai Guo Wang ◽  
Dong Lin Yang ◽  
Peng Zhao
Keyword(s):  
Real Time ◽  
Influence Factors ◽  
Experimental Result ◽  
Detection Accuracy ◽  
Cast Aluminum ◽  
X Ray ◽  
Imaging Quality ◽  
Real Time Imaging ◽  
Detection Technology ◽  
Imaging Detection

x-ray real time imaging detection technology is a kind of important way for industrial nondestructive test. On the basis of basic theory on X-ray detection, The influence factors on x-ray real time imaging detection precision is analyzed in this article. Through analysis for the focus of X-ray source and the unintelligibility of geometric image, the relation between the optimal amplification multiple and the imaging quality is presented and the electric collimator to solve the influence on imaging quality from the scattered ray. The experimental result shows that the detection resolution ratio is up to 50PL/cm and the sensitivity is up to 1.4 % to solve the on-line real time detection for pore, inclusion and looseness and verify the application feasibility in the detection of cast aluminum parts for x-ray real time imaging detection technology.

Sign in / Sign up

Export Citation Format

Share Document