Edge-Network-Assisted Real-Time Object Detection Framework for Autonomous Driving

Kim, Seung-Wook; Ko, Keunsoo; Ko, Haneul; Leung, Victor C. M.

doi:10.1109/mnet.011.2000248

Cited by 33 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dai et al [15] designed an object recognition method for efficient and reliable object recognition in thermal infrared (TIR) images named TIRNet, which is based on convolution neural networks (CNNs). Kim et al [16] developed an edge-network-enabled real-time object detection framework (EODF). In EODF, AVs extract the region of interest (RoI) of an image taken while the channel quality is not adequately better to support real-time object recognition.…”

Section: Related Workmentioning

confidence: 99%

Computational Intelligence with Wild Horse Optimization Based Object Recognition and Classification Model for Autonomous Driving Systems

et al. 2022

View full text Add to dashboard Cite

Presently, autonomous systems have gained considerable attention in several fields such as transportation, healthcare, autonomous driving, logistics, etc. It is highly needed to ensure the safe operations of the autonomous system before launching it to the general public. Since the design of a completely autonomous system is a challenging process, perception and decision-making act as vital parts. The effective detection of objects on the road under varying scenarios can considerably enhance the safety of autonomous driving. The recently developed computational intelligence (CI) and deep learning models help to effectively design the object detection algorithms for environment perception depending upon the camera system that exists in the autonomous driving systems. With this motivation, this study designed a novel computational intelligence with a wild horse optimization-based object recognition and classification (CIWHO-ORC) model for autonomous driving systems. The proposed CIWHO-ORC technique intends to effectively identify the presence of multiple static and dynamic objects such as vehicles, pedestrians, signboards, etc. Additionally, the CIWHO-ORC technique involves the design of a krill herd (KH) algorithm with a multi-scale Faster RCNN model for the detection of objects. In addition, a wild horse optimizer (WHO) with an online sequential ridge regression (OSRR) model was applied for the classification of recognized objects. The experimental analysis of the CIWHO-ORC technique is validated using benchmark datasets, and the obtained results demonstrate the promising outcome of the CIWHO-ORC technique in terms of several measures.

show abstract

Section: Related Workmentioning

confidence: 99%

Computational Intelligence with Wild Horse Optimization Based Object Recognition and Classification Model for Autonomous Driving Systems

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Such edge detection has important implication for various applications that require realtime image processing (e.g., autonomous driving). [83]…”

Section: Introductionmentioning

confidence: 99%

Dual‐Modal Optoelectronic Synaptic Devices with Versatile Synaptic Plasticity

Wang

Zhu

et al. 2021

Adv Funct Materials

View full text Add to dashboard Cite

Optoelectronic synaptic devices that mimic biological synapses are critical building blocks of artificial neural networks (ANN) based on optoelectronic integration. Here it is shown that an optoelectronic synaptic device based on the hybrid structure of silicon nanocrystals (Si NCs) and poly(3-hexylthiophene) (P3HT) can work with dual modes, exhibiting versatile synaptic plasticity. In the three-terminal mode, the device is a synaptic transistor, which has wavelength-selective synaptic plasticity due to potential wells enabled by the Si NCs/P3HT hybrid structure. In the two-terminal mode, it is a synaptic metal-oxide-semiconductor (MOS) device, which is capable of mimicking spike-rate-dependent plasticity (SRDP) and metaplasticity with optical stimulation. Based on the wavelength-selective synaptic plasticity a light-stimulated ANN is proposed to recognize handwritten digits with an accuracy of around 90.4%. In addition, the SRDP and metaplasticity may be well used for the simulation of edge detection of images, facilitating real-time image processing.

show abstract

“…The former work up-samples the convolution features of deep layer to the shallow deconvolution layers to enhance the contextual cues, and the later work uses channel split and shuffle modules in the encoder to reduce the number of parameters, and introduces an attention module in the decoder to improve the accuracy. By directly designing lightweight modules, a good balance between the accuracy and the size of the model can be achieved, these lightweight networks can be well combined with tasks in autonomous driving, like [32]. Such these well-designed modules or networks [33], [34], [35], [36], [37], can normally run on laboratory host machines.…”

Section: Introductionmentioning

confidence: 99%

Group channel pruning and spatial attention distilling for object detection

Chu

Bai

et al. 2022

Appl Intell

View full text Add to dashboard Cite

Due to the over-parameterization of neural networks, many model compression methods based on pruning and quantization have emerged. They are remarkable in reducing the size, parameter number, and computational complexity of the model. However, most of the models compressed by such methods need the support of special hardware and software, which increases the deployment cost. Moreover, these methods are mainly used in classification tasks, and rarely directly used in detection tasks. To address these issues, for the object detection network we introduce a three-stage model compression method: dynamic sparse training, group channel pruning, and spatial attention distilling. Firstly, to select out the unimportant channels in the network and maintain a good balance between sparsity and accuracy, we put forward a dynamic sparse training method, which introduces a variable sparse rate, and the sparse rate will change with the training process of the network. Secondly, to reduce the effect of pruning on network accuracy, we propose a novel pruning method called group channel pruning. In particular, we divide the network into multiple groups according to the scales of the feature layer and the similarity of module structure in the network, and then we use different pruning thresholds to prune the channels in each group. Finally, to recover the accuracy of the pruned network, we use an improved knowledge distillation method for the pruned network. Especially, we extract spatial attention information from the feature maps of specific scales in each group as knowledge for distillation. In the experiments, we use YOLOv4 as the object detection network and PASCAL VOC as the training dataset. Our method reduces the parameters of the model by 64.7% and the calculation by 34.9%. When the input image size is 416×416, compared with the original network model with 256MB size and 87.1 accuracies, our compressed model achieves 86.6 accuracies with 90MB size. To demonstrate the generality of our method, we replace the backbone to Darknet53 and Mobilenet and also achieve satisfactory compression results.

show abstract

Edge-Network-Assisted Real-Time Object Detection Framework for Autonomous Driving

Cited by 33 publications

References 12 publications

Computational Intelligence with Wild Horse Optimization Based Object Recognition and Classification Model for Autonomous Driving Systems

Computational Intelligence with Wild Horse Optimization Based Object Recognition and Classification Model for Autonomous Driving Systems

Dual‐Modal Optoelectronic Synaptic Devices with Versatile Synaptic Plasticity

Group channel pruning and spatial attention distilling for object detection

Contact Info

Product

Resources

About