Using C3D to Detect Rear Overtaking Behavior

Tseng, Ching-Kai; Liao, Chungpin; Shen, Po-Chun; Guo, Jiun-In

doi:10.1109/icip.2019.8802963

Cited by 4 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method was evaluated using five classification models (Table 2), six regression models (Table 3) and three semantic similarity models (Table 4). We used five image classification models: LeNet5 [46], DenseNet201 [47], ResNet152 [48], VGG16 [49], and C3D [50]. We used three regression models: the recurrent neural network (RNN), the long short-term memory network (LSTM), and the gated recurrent unit network (GRU) [51].…”

Section: A Experimental Setupmentioning

confidence: 99%

Automated Quantization and Retraining for Neural Network Models Without Labeled Data

et al. 2022

View full text Add to dashboard Cite

Deploying neural network models to edge devices is becoming increasingly popular because such deployment decreases the response time and ensures better data privacy of services. However, running large models on edge devices poses challenges because of limited computing resources and storage space. Researchers have therefore proposed various model compression methods to reduce the model size. To balance the trade-off between model size and accuracy, conventional model compression methods require manual effort to find the optimal configuration that reduces the model size without significant degradation of accuracy. In this article, we propose a method to automatically find the optimal configurations for quantization. The proposed method suggests multiple compression configurations that produce models with different size and accuracy, from which users can select the configurations that suit their use cases. Additionally, we propose a retraining method that does not require any labeled datasets for retraining. We evaluated the proposed method using various neural network models for classification, regression and semantic similarity tasks, and demonstrated that the proposed method reduced the size of models by at least 30% while maintaining less than 1% loss of accuracy. We compared the proposed method with state-of-theart automated compression methods, and showed that it can provide better compression configurations than existing methods.

show abstract

Section: A Experimental Setupmentioning

confidence: 99%

Automated Quantization and Retraining for Neural Network Models Without Labeled Data

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In [ 53 ], the results report the overtaking detection with 98 true positives, 5 false positives, 3 false negatives, at the precision and recall rates of 95.1% and 97.0%, respectively. The work in [ 54 ] shows the precision and recall rates of 96.3% and 86.9%, respectively. In the proposed method, the precision rates for ’city traffic’, ’highway’, and ’night’ are 88.7%, 98.8%, and 90.2%, respectively.…”

Section: Implementation and Experimentsmentioning

confidence: 99%

A Vision-Based Driver Assistance System with Forward Collision and Overtaking Detection

Lin

Dai

et al. 2020

Sensors

View full text Add to dashboard Cite

One major concern in the development of intelligent vehicles is to improve the driving safety. It is also an essential issue for future autonomous driving and intelligent transportation. In this paper, we present a vision-based system for driving assistance. A front and a rear on-board camera are adopted for visual sensing and environment perception. The purpose is to avoid potential traffic accidents due to forward collision and vehicle overtaking, and assist the drivers or self-driving cars to perform safe lane change operations. The proposed techniques consist of lane change detection, forward collision warning, and overtaking vehicle identification. A new cumulative density function (CDF)-based symmetry verification method is proposed for the detection of front vehicles. The motion cue obtained from optical flow is used for overtaking detection. It is further combined with a convolutional neural network to remove repetitive patterns for more accurate overtaking vehicle identification. Our approach is able to adapt to a variety of highway and urban scenarios under different illumination conditions. The experiments and performance evaluation carried out on real scene images have demonstrated the effectiveness of the proposed techniques.

show abstract

Intelligent advice system for human drivers to prevent overtaking accidents in roads

Perumal

Wang

Sujasree

et al. 2022

Expert Systems with Applications

View full text Add to dashboard Cite

Using C3D to Detect Rear Overtaking Behavior

Cited by 4 publications

References 2 publications

Automated Quantization and Retraining for Neural Network Models Without Labeled Data

Automated Quantization and Retraining for Neural Network Models Without Labeled Data

A Vision-Based Driver Assistance System with Forward Collision and Overtaking Detection

Intelligent advice system for human drivers to prevent overtaking accidents in roads

Contact Info

Product

Resources

About