scholarly journals Research on driverless vehicle vision algorithm

2021 ◽  
Vol 336 ◽  
pp. 06001
Author(s):  
Xinchao Liu ◽  
Ying Yan ◽  
Haiyun Gan
Keyword(s):  
Target Detection ◽  
Learning Algorithm ◽  
Detection Algorithm ◽  
Obstacle Detection ◽  
Urban Traffic ◽  
Experimental Results ◽  
Deep Learning Algorithm ◽  
Deep Model ◽  
Traffic Environment ◽  
Vision Algorithm

Obstacle detection in complex urban traffic environment has become an important part of unmanned vehicle optimization, and its complexity brings great challenges to the reliability of unmanned target detection. YOLOv3 in deep learning algorithm has a good detection effect in target detection, but it has certain defects in detecting targets in complex urban traffic environment. In this paper, the spatial pyramid module is added to YOLOv3 to improve the extraction of data features of the deep model. Then, on the basis of optimized network, the target detection algorithm is streamlined by combining layer pruning and channel pruning. The streamlined algorithm is called YOLOv3-SPP3-Tiny. Comparing the experimental results of YOLOv3-SPP3-tiny and YOLOv3 on Street Scenes dataset, the Precision is improved by 2.77%, the average precision (mAP) is increased by 0.87%, the Total BFLOPS is reduced by 94.49%, and the Inference time is reduced by 80.39%. Experimental results show that the model YOLOv3-SPP3-tiny algorithm is more conducive to unmanned object detection in complex urban road environment.

scholarly journals Research on pedestrian detection algorithm in driverless urban traffic environment

2021 ◽  
Vol 336 ◽  
pp. 06002
Author(s):  
Xinchao Liu ◽  
Ying Yan ◽  
Haiyun Gan
Keyword(s):  
Target Detection ◽  
Pedestrian Detection ◽  
Human Head ◽  
Detection Algorithm ◽  
Input Image ◽  
Urban Traffic ◽  
Image Size ◽  
Data Set ◽  
Traffic Environment ◽  
Pruning Strategy

Pedestrian detection in urban traffic environment is an important field of driverless vehicle research. Due to the variability of traffic flow, target detection algorithm cannot extract complete feature information, which brings great challenges to driverless pedestrian detection. Target detection algorithm YOLOv4 has excellent detection performance in object detection, but it is not perfect in identifying semi-blocked pedestrians. In this paper, the Spatial Pyramid Pooling was added in front of the third yolo detection head module of YOLOv4 to optimize the extraction of deep network features. Then, on the basis of optimizing the network, pruning strategy was adopted to simplify the target detection algorithm, which was called TidyYOLOv4.TidyYOLOv4 and YOLOv4 (network set input image size is 864×864) were compared on the self-made human head data set. Total BFLOPS decreased by 95.04% and Inference time decreased by 82.82%. The above experimental results show that the optimized TidyYOLOv4 algorithm is more suitable for driverless pedestrian detection in urban traffic environment.

Moving Target Detection Based on Principle of Connectivity and Texture Gradient

2012 ◽  
Vol 605-607 ◽  
pp. 2117-2120
Author(s):  
Min Huang ◽  
Yang Zhang ◽  
Gang Chen ◽  
Guo Feng Yang
Keyword(s):  
Target Detection ◽  
Detection Algorithm ◽  
Experimental Results ◽  
Texture Gradient ◽  
Moving Target ◽  
Moving Target Detection ◽  
Gradient Information ◽  
Target Segmentation ◽  
Target Profile

In target detection, “hole” phenomenon is present in the detection result, and the shadow is difficult to remove. To solve these problems, we propose a target detection algorithm based on principle of connectivity and texture gradient. Firstly, we use the connectivity principle to find the largest target prospects connection area to get a complete target contour, secondly we use target texture gradient information to further remove the shadow of the target. At last, the experimental results show that the algorithm can obtain a clear target profile and improve the accuracy of the moving target segmentation.

scholarly journals Obstacle Detection in Cluttered Traffic Environment Based on Candidate Generation and Classification

2006 ◽  
Vol 1 (4) ◽  
pp. 93 ◽  
Author(s):  
Qing Li ◽  
F.C. Sun
Keyword(s):  
Vehicle Detection ◽  
Obstacle Detection ◽  
Experimental Results ◽  
Geometrical Features ◽  
Traffic Environment ◽  
Novel Method ◽  
Shadow Cast

A novel method to detect vehicles is presented in the paper. Assumption of the vehicle is made using the geometrical features of the vehicle rear by the statistical histogram. Then hypothesis is verified using the property of the shadow cast by the car according to a prior acknowledgement of traffic scene. Finally, the vehicle detection is realized by hypothesis and verification of objects. The experimental results show the efficiency and feasibility of the method.

scholarly journals A study of Grammar Analysis in English Teaching With Deep Learning Algorithm

2020 ◽  
Vol 15 (18) ◽  
pp. 20
Author(s):  
Gang Zhang
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Experimental Results ◽  
P Value ◽  
Analysis Method ◽  
English Teaching ◽  
Deep Learning Algorithm ◽  
R Value ◽  
Grammar Analysis ◽  
Teaching Grammar

In English teaching, grammar is a very important part. Based on the seq2seq model, a grammar analysis method combining the attention mechanism, word embedding and CNN seq2seq was designed using the deep learning algorithm, then the algorithm training was completed on NUCLE, and it was tested on CoNIL-2014. The experimental results showed that of seq2seq+attention improved 33.43% compared to the basic seq2seq; in the comparison between the method proposed in this study and CAMB, the P value of the former was 59.33% larger than that of CAMB, the R value was 8.9% larger, and the value of was 42.91% larger. Finally, in the analysis of the actual students' grammar homework, the proposed method also showed a good performance. The experimental results show that the method designed in this study is effective in grammar analysis and can be applied and popularized in actual English teaching.

scholarly journals Classification of Shellfish Recognition Based on Improved Faster R-CNN Framework of Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Yiran Feng ◽  
Xueheng Tao ◽  
Eung-Joo Lee
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Experimental Tests ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Multiple Objects ◽  
Detection Model ◽  
Deep Learning Algorithm ◽  
Quality Sorting

In view of the current absence of any deep learning algorithm for shellfish identification in real contexts, an improved Faster R-CNN-based detection algorithm is proposed in this paper. It achieves multiobject recognition and localization through a second-order detection network and replaces the original feature extraction module with DenseNet, which can fuse multilevel feature information, increase network depth, and avoid the disappearance of network gradients. Meanwhile, the proposal merging strategy is improved with Soft-NMS, where an attenuation function is designed to replace the conventional NMS algorithm, thereby avoiding missed detection of adjacent or overlapping objects and enhancing the network detection accuracy under multiple objects. By constructing a real contexts shellfish dataset and conducting experimental tests on a vision recognition seafood sorting robot production line, we were able to detect the features of shellfish in different scenarios, and the detection accuracy was improved by nearly 4% compared to the original detection model, achieving a better detection accuracy. This provides favorable technical support for future quality sorting of seafood using the improved Faster R-CNN-based approach.

scholarly journals Multicenter Validation of a Deep Learning Detection Algorithm for Focal Cortical Dysplasia

Neurology ◽  
2021 ◽  
pp. 10.1212/WNL.0000000000012698
Author(s):  
Ravnoor Singh Gill ◽  
Hyo-Min Lee ◽  
Benoit Caldairou ◽  
Seok-Jun Hong ◽  
Carmen Barba ◽  
...  
Keyword(s):  
Deep Learning ◽  
Risk Stratification ◽  
Learning Algorithm ◽  
Focal Cortical Dysplasia ◽  
Detection Algorithm ◽  
Cortical Dysplasia ◽  
False Positives ◽  
Class Iii ◽  
Deep Learning Algorithm ◽  
Independent Cohort

Objective.To test the hypothesis that a multicenter-validated computer deep learning algorithm detects MRI-negative focal cortical dysplasia (FCD).Methods.We used clinically-acquired 3D T1-weighted and 3D FLAIR MRI of 148 patients (median age, 23 years [range, 2-55]; 47% female) with histologically-verified FCD at nine centers to train a deep convolutional neural network (CNN) classifier. Images were initially deemed as MRI-negative in 51% of cases, in whom intracranial EEG determined the focus. For risk stratification, the CNN incorporated Bayesian uncertainty estimation as a measure of confidence. To evaluate performance, detection maps were compared to expert FCD manual labels. Sensitivity was tested in an independent cohort of 23 FCD cases (13±10 years). Applying the algorithm to 42 healthy and 89 temporal lobe epilepsy disease controls tested specificity.Results.Overall sensitivity was 93% (137/148 FCD detected) using a leave-one-site-out cross-validation, with an average of six false positives per patient. Sensitivity in MRI-negative FCD was 85%. In 73% of patients, the FCD was among the clusters with the highest confidence; in half it ranked the highest. Sensitivity in the independent cohort was 83% (19/23; average of five false positives per patient). Specificity was 89% in healthy and disease controls.Conclusions.This first multicenter-validated deep learning detection algorithm yields the highest sensitivity to date in MRI-negative FCD. By pairing predictions with risk stratification this classifier may assist clinicians to adjust hypotheses relative to other tests, increasing diagnostic confidence. Moreover, generalizability across age and MRI hardware makes this approach ideal for pre-surgical evaluation of MRI-negative epilepsy.Classification of evidence.This study provides Class III evidence that deep learning on multimodal MRI accurately identifies FCD in epilepsy patients initially diagnosed as MRI-negative.

scholarly journals Geographic Generalization in Airborne RGB Deep Learning Tree Detection

2019 ◽  
Author(s):  
Ben. G. Weinstein ◽  
Sergio Marconi ◽  
Stephanie A. Bohlman ◽  
Alina Zare ◽  
Ethan P. White
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Forest Type ◽  
Detection Algorithm ◽  
Forest Types ◽  
Individual Tree ◽  
Tree Detection ◽  
Deep Learning Algorithm ◽  
Local Site ◽  
Using Data

AbstractTree detection is a fundamental task in remote sensing for forestry and ecosystem ecology applications. While many individual tree segmentation algorithms have been proposed, the development and testing of these algorithms is typically site specific, with few methods evaluated against data from multiple forest types simultaneously. This makes it difficult to determine the generalization of proposed approaches, and limits tree detection at broad scales. Using data from the National Ecological Observatory Network we extend a recently developed semi-supervised deep learning algorithm to include data from a range of forest types, determine whether information from one forest can be used for tree detection in other forests, and explore the potential for building a universal tree detection algorithm. We find that the deep learning approach works well for overstory tree detection across forest conditions, outperforming conventional LIDAR-only methods in all forest types. Performance was best in open oak woodlands and worst in alpine forests. When models were fit to one forest type and used to predict another, performance generally decreased, with better performance when forests were more similar in structure. However, when models were pretrained on data from other sites and then fine-tuned using a small amount of hand-labeled data from the evaluation site, they performed similarly to local site models. Most importantly, a universal model fit to data from all sites simultaneously performed as well or better than individual models trained for each local site. This result suggests that RGB tree detection models that can be applied to a wide array of forest types at broad scales should be possible.

scholarly journals Classification of Magnetic Tile Surface Defects Based on Efficientnet Network with Attention

2021 ◽  
Vol 2137 (1) ◽  
pp. 012062
Author(s):  
Chengshuai Fan
Keyword(s):  
Classification Accuracy ◽  
Surface Defects ◽  
Learning Algorithm ◽  
Complex Surface ◽  
Detection Algorithm ◽  
Image Features ◽  
Low Contrast ◽  
Deep Learning Algorithm ◽  
Model Size

Abstract The magnetic tile image has the characteristics of uneven illumination, complex surface texture, and low contrast. Aiming at the problem that the traditional defect detection algorithm is difficult to accurately identify the defects, and the deep learning algorithm is difficult to balance the classification accuracy and the size of the speed model, a defect classification algorithm based on attention-based EfficientNet is proposed. The algorithm first enhances the network’s spatial and location information for image features by integrating the Convolutional Block Attention Module, and improves the network’s ability to identify defects. Then, on this basis, Criss-Cross Attention is added to the network, so that the network can better the context information of the horizontal and vertical cross of image features, so that each pixel can finally capture the full image dependency of all pixels. Experimental results show that the algorithm has higher classification accuracy than EfficientNet-B0, reached 99.11%, and has a better balance between accuracy, speed and model size than other classification models.

scholarly journals Development and Validation of Suspicious Liver Lesion Deep Learning Algorithm for Computed Tomography

2021 ◽  
Author(s):  
Jacob Johnson ◽  
Kaneel Senevirathne ◽  
Lawrence Ngo
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Small Sample Size ◽  
Liver Lesion ◽  
The United States ◽  
Detection Algorithm ◽  
Small Sample ◽  
Lesion Detection ◽  
Liver Lesions ◽  
Deep Learning Algorithm

In this work, we report the results of a deep-learning based liver lesion detection algorithm. While several liver lesion segmentation and classification algorithms have been developed, none of the previous work has focused on detecting suspicious liver lesions. Furthermore, their generalizability remains a pitfall due to their small sample size and sample homogeneity. Here, we developed and validated a highly generalizable deep-learning algorithm for detection of suspicious liver lesions. The algorithm was trained and tested on a diverse dataset containing CT exams from over 2,000 hospital sites in the United States. Our final model achieved an AUROC of 0.84 with a specificity of 0.99 while maintaining a sensitivity of 0.33.

scholarly journals Abnormal Behavior Recognition in Classroom Pose Estimation of College Students Based on Spatiotemporal Representation Learning

2021 ◽  
Vol 38 (1) ◽  
pp. 89-95
Author(s):  
Yunfang Xie ◽  
Su Zhang ◽  
Yingdi Liu
Keyword(s):  
College Students ◽  
Learning Algorithm ◽  
Three Dimensional ◽  
Representation Learning ◽  
Detection Algorithm ◽  
Abnormal Behavior ◽  
Surveillance Video ◽  
Deep Learning Algorithm ◽  
Spatiotemporal Representation ◽  
Abnormal Behaviors

Artificial intelligence and fifth generation (5G) technology are widely adopted to evaluate the classroom poses of college students, with the help of campus video surveillance equipment. To ensure the effective learning in class, it is important to detect and intervene in abnormal behaviors like sleeping and using cellphones in time. Based on spatiotemporal representation learning, this paper presents a deep learning algorithm to evaluate classroom poses of college students. Firstly, feature engineering was adopted to mine the moving trajectories of college students, which were used to determine student distribution and establish a classroom prewarning system. Then, k-means clustering (KMC) was employed for cluster analysis on different student groups, and identify the features of each group. For a specific student group, the classroom surveillance video was decomposed into several frames; the edge of each frame was extracted by edge detection algorithm, and imported to the proposed convolutional neural network (CNN). Experimental results show that our algorithm is 5% more accurate than the benchmark three-dimensional CNN (C3D), making it an effective tool to recognize abnormal behaviors of college students in class.

Sign in / Sign up

Export Citation Format

Share Document