MobileYOLO: Real-Time Object Detection Algorithm in Autonomous Driving Scenarios

Zhou, Yan; Wen, Sijie; Wang, Dongli; Meng, Jiangnan; Mu, Jinzhen; Irampaye, Richard

doi:10.3390/s22093349

Cited by 20 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, such an architecture is lightweight and can be deployed in field applications using mobile devices. 49,50 Recent comparative reviews agree that YOLOv2 gives the best compromise between the processing time and the detection accuracy for real-time drone detection. 33 Successful applications of MobileNet-v2 and YOLOv2 have been presented in literature.…”

Section: The Mobilenet-v2 and Yolov2 Object Detection Networkmentioning

confidence: 99%

Bio-inspired enhancement for optical detection of drones using convolutional neural networks

Luesutthiviboon,

de Croon,

Altena

et al. 2023

Artificial Intelligence for Security and Defence Applications

View full text Add to dashboard Cite

Threats posed by drones urge defence sectors worldwide to develop drone detection systems. Visible-light and infrared cameras complement other sensors in detecting and identifying drones. Application of Convolutional Neural Networks (CNNs), such as the You Only Look Once (YOLO) algorithm, are known to help detect drones in video footage captured by the cameras quickly, and to robustly differentiate drones from other flying objects such as birds, thus avoiding false positives. However, using still video frames for training the CNN may lead to low drone-background contrast when it is flying in front of clutter, and omission of useful temporal data such as the flight trajectory. This deteriorates the drone detection performance, especially when the distance to the target increases. This work proposes to pre-process the video frames using a Bio-Inspired Vision (BIV) model of insects, and to concatenate the pre-processed video frame with the still frame as input for the CNN. The BIV model uses information from preceding frames to enhance the moving target-to-background contrast and embody the target’s recent trajectory in the input frames. An open benchmark dataset containing infrared videos of small drones (< 25 kg) and other flying objects is used to train and test the proposed methodology. Results show that, at a high sensor-to-target distance, the YOLO algorithms trained on BIV-processed frames and concatenation of the BIV-processed frames with still frames increase the Average Precision (AP) to 0.92 and 0.88, respectively, compared to 0.83 when it is trained on still frames alone.

show abstract

Section: The Mobilenet-v2 and Yolov2 Object Detection Networkmentioning

confidence: 99%

Bio-inspired enhancement for optical detection of drones using convolutional neural networks

Luesutthiviboon,

de Croon,

Altena

et al. 2023

Artificial Intelligence for Security and Defence Applications

View full text Add to dashboard Cite

show abstract

“…A series of models have emerged, such as SqueezeNet, ShuffleNet [ 17 ], Xception [ 18 ], and MobileNet [ 19 , 20 ], which make it possible for embedded and other edge devices to run deep learning models directly. Zhou et al [ 5 ] proposed the MobileYOLO model, which used the mobilenet to effectively reduce model parameters. Zhao et al [ 21 ] proposed an improved YOLO model to adapt to real-time detection in a special natural geographical environment.…”

Section: Related Workmentioning

confidence: 99%

“…At present, the remarkable progress of computer vision and computation tools have provided theoretical and technical support for autonomous environmental perception [ 2 ]. Therefore, vision-based object detection is a key means of autonomous environmental perception [ 3 , 4 ], and its detection performances, such as accuracy, speed, efficiency, and robustness, are very important for the detection of vehicles, pedestrians, and obstacles in traffic scenes [ 5 , 6 ].…”

Section: Introductionmentioning

confidence: 99%

A Lightweight Vehicle-Pedestrian Detection Algorithm Based on Attention Mechanism in Traffic Scenarios

Zhang

Zhou

Zhao

et al. 2022

Sensors

View full text Add to dashboard Cite

Object detection is a critical technology of environmental perception for autonomous driving vehicle. The Convolutional Neural Network has gradually become a powerful tool in the field of vehicle detection because of its powerful ability of feature extraction. In aiming to reach the balance between speed and accuracy of detection in complex traffic scenarios, this paper proposes an improved lightweight and high-performance vehicle–pedestrian detection algorithm based on the YOLOv4. Firstly, the backbone network CSPDarknet53 is replaced by MobileNetv2 to reduce the number of parameters and raise the capability of feature extraction. Secondly, the method of multi-scale feature fusion is used to realize the information interaction among different feature layers. Finally, a coordinate attention mechanism is added to focus on the region of interest in the image by way of weight adjustment. The experimental results show that this improved model has a great performance in vehicle–pedestrian detection in traffic scenarios. Experimental results on PASCAL VOC datasets show that the improved model’s mAP is 85.79% and speed is 35FPS, which has an increase of 4.31% and 16.7% compared to YOLOv4. Furthermore, the improved YOLOv4 model maintains a great balance between detection accuracy and speed on different datasets, indicating that it can be applied to vehicle–pedestrian detection in traffic scenarios.

show abstract

“…Chen et al [23] proposed a DW-YOLO algorithm that improves vehicle object detection performance by increasing the depth and width of the network. Zhou et al [24] proposed a lightweight MobileYOLO algorithm that reduces the number of parameters and improves detection speed. Wang et al [25] applied MobileNet to a YOLOv4 network for driving scenarios and achieved a detection speed of 35 FPS.…”

Section: Introductionmentioning

confidence: 99%

MCS-YOLO: A Multiscale Object Detection Method for Autonomous Driving Road Environment Recognition

Cao

Peng

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Object detection and recognition of road scenes are crucial tasks of the autonomous driving environmental perception system. The low inference speed and accuracy in object detection models hinder the development of autonomous driving technology. Searching for improvement of detection accuracy and speed is still a challenging task. For solving these problems, we proposed an MCS-YOLO algorithm. Firstly, a coordinate attention module is inserted into the backbone to aggregate the feature map's spatial coordinate and cross-channel information. Then, we designed a multiscale small object detection structure to improve the recognition sensitivity of dense small object. Finally, we applied the Swin Transformer structure to the CNN to enable the network to focus on contextual spatial information. Conducting ablation study on the autonomous driving dataset BDD100K, MCS-YOLO algorithm achieves a mean average precision of 53.6% and a recall rate of 48.3%, which are 4.3% and 3.9% better than the YOLOv5s algorithm respectively. In addition, it can achieve real-time detection speed of 55 frames per second in a real scene. The results show that the MCS-YOLO algorithm is effective and superior in the task of automatic driving object detection.

show abstract

MobileYOLO: Real-Time Object Detection Algorithm in Autonomous Driving Scenarios

Cited by 20 publications

References 26 publications

Bio-inspired enhancement for optical detection of drones using convolutional neural networks

Bio-inspired enhancement for optical detection of drones using convolutional neural networks

A Lightweight Vehicle-Pedestrian Detection Algorithm Based on Attention Mechanism in Traffic Scenarios

MCS-YOLO: A Multiscale Object Detection Method for Autonomous Driving Road Environment Recognition

Contact Info

Product

Resources

About