Tiny YOLO Optimization Oriented Bus Passenger Object Detection

Zhang, Shuo; Wu, Yanxia; Men, Chaoguang; Li, Xiaosong

doi:10.1049/cje.2019.11.002

Cited by 48 publications

(28 citation statements)

References 10 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although a high-capacity network model can improve the segmentation accuracy, it sacrifices performance and running speed at the expense of mobile edge devices. In recent literature, many different network architectures have been constructed, the applicability of depth separable convolution in the lightweight YOLO has been proven [31,32], and it has been demonstrated that the usage of residual blocks can better extract features [33,34]. However, the detection network can only locate the target in a small area, but not achieve the pixel-level segmentation effect, and it is difficult to present the contour shape completely, affecting the precision of subsequent harvest.…”

Section: Introductionmentioning

confidence: 99%

A Method of Fast Segmentation for Banana Stalk Exploited Lightweight Multi-Feature Fusion Deep Neural Network

Chen¹,

Zhang²,

Zhu³

et al. 2021

Machines

View full text Add to dashboard Cite

In an orchard environment with a complex background and changing light conditions, the banana stalk, fruit, branches, and leaves are very similar in color. The fast and accurate detection and segmentation of a banana stalk are crucial to realize the automatic picking using a banana picking robot. In this paper, a banana stalk segmentation method based on a lightweight multi-feature fusion deep neural network (MFN) is proposed. The proposed network is mainly composed of encoding and decoding networks, in which the sandglass bottleneck design is adopted to alleviate the information a loss in high dimension. In the decoding network, a different sized dilated convolution kernel is used for convolution operation to make the extracted banana stalk features denser. The proposed network is verified by experiments. In the experiments, the detection precision, segmentation accuracy, number of parameters, operation efficiency, and average execution time are used as evaluation metrics, and the proposed network is compared with Resnet_Segnet, Mobilenet_Segnet, and a few other networks. The experimental results show that compared to other networks, the number of network parameters of the proposed network is significantly reduced, the running frame rate is improved, and the average execution time is shortened.

show abstract

Section: Introductionmentioning

confidence: 99%

A Method of Fast Segmentation for Banana Stalk Exploited Lightweight Multi-Feature Fusion Deep Neural Network

Chen¹,

Zhang²,

Zhu³

et al. 2021

Machines

View full text Add to dashboard Cite

show abstract

“…Tiny object detection is an very meaningful implementation in real-world application [8], [9], [10], [11], [12]. The feature pyramid network (FPN) is widely employed in deep learning for small object detection [13].…”

Section: Previous Workmentioning

confidence: 99%

Feature Rescaling and Fusion for Tiny Object Detection

Liu

Han

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Recent years have witnessed rapid developments on computer vision, however, there are still challenges in detecting tiny objects in a large-scale background. The tiny objects knowledge become sparse and weak due to their tiny size, which makes the tiny objects difficult to be detected with the common approaches. In this paper, a new network named Specific Characteristics based Feature Rescaling and Fusion (SFRF) is designed to detect tiny persons in a broad horizon and massive background. Different from the methods in general, a Nonparametric Adaptive Dense Perceiving Algorithm (NADPA) is designed to automatically select and generate a new resized feature map with the high density distribution of tiny objects. Then, a method called Many-For-One strategy is used for feature fusion of the feature pyramid network (FPN) layers to improve the feature representation and detection. Finally, an ensemble model method named hierarchical Coarse-to-fine mechanism is designed based on the proposed methods to further improve the performance. The experiments demonstrate that the proposed approach achieves an obvious performance improvement on tiny object detection than the existing approaches, and our approach has been awarded as the 1st-place in the first large-scale Tiny Object Detection (TOD) challenge.

show abstract

“…e whole network consists of nine convolutional layers, six maximum pooling layers, and one detection layer. e network convolution structure is shown in Table 1 [14]. e performance of tiny YOLO convolution neural network in target detection is tested by using a bus passenger test set containing 12,749 pictures.…”

Section: E Basis Of Convolutional Network Model Optimizationmentioning

confidence: 99%

Channel Compression Optimization Oriented Bus Passenger Object Detection

Zhang

Men

et al. 2020

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

Bus passenger flow information can facilitate scientific dispatching plans, which is essential to decision making and operation performance evaluation. Real-time acquisition of bus passenger flow information is an indispensable part for bus intellectualization. The method of passenger flow statistics in bus video monitoring scene based on deep convolution neural network can provide rich information for passenger flow statistics. In order to adapt to the real scenario of mobile and embedded devices on buses, and to consider the bandwidth limitation, this paper uses a lightweight network model M7, which is suitable for the vehicle system. Based on the classic network model tiny YOLO, the model is optimized by a depthwise separable convolution method. The optimized network model M7 reduces the number of parameters and improves the detection speed, while maintaining a low loss in detection accuracy. As such, the network model M7 is compressed and further optimized by removing redundant channels. The experimental results show that the detection speed of the network model target recognition after channel compression is 40%, which is faster than the precious channel compression on the premise of ensuring detection.

show abstract

Tiny YOLO Optimization Oriented Bus Passenger Object Detection

Cited by 48 publications

References 10 publications

A Method of Fast Segmentation for Banana Stalk Exploited Lightweight Multi-Feature Fusion Deep Neural Network

A Method of Fast Segmentation for Banana Stalk Exploited Lightweight Multi-Feature Fusion Deep Neural Network

Feature Rescaling and Fusion for Tiny Object Detection

Channel Compression Optimization Oriented Bus Passenger Object Detection

Contact Info

Product

Resources

About