Faster-YOLO: An accurate and faster object detection method

@article{Yin2020FasterYOLOAA,
  title={Faster-YOLO: An accurate and faster object detection method},
  author={Yunhua Yin and Huifang Li and Wei Fu},
  journal={Digit. Signal Process.},
  year={2020},
  volume={102},
  pages={102756}
}
YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs
TLDR
A novel edge GPU friendly module for multi-scale feature interaction by exploiting missing combinatorial connections between various feature scales in existing state-of-the-art methods and a novel transfer learning backbone adoption inspired by the changing translational information flow across various tasks are proposed.
RFSOD: a lightweight single-stage detector for real-time embedded applications to detect small-size objects
TLDR
A convolutional neural network architecture based on YOLO is proposed to enhance small objects' detection performance and is developed as a lightweight network to suit real-time applications and can run smoothly on single-board computers such as Jetson Nano, Tx2, Raspberry Pi and the like.
Automatic Bunch Detection in White Grape Varieties Using YOLOv3, YOLOv4, and YOLOv5 Deep Learning Algorithms
Over the last few years, several Convolutional Neural Networks for object detection have been proposed, characterised by different accuracy and speed. In viticulture, yield estimation and prediction
A hybrid tiny YOLO v4-SPP module based improved face mask detection vision system
TLDR
A novel face mask vision system that is based on an improved tiny YOLO v4 object detector that is capable of accurate detection of a mask on the face region in real-time surveillance applications where visibility of complete face area is a guideline.
A Comparison of YOLO and Mask R-CNN for Segmenting Head and Tail of Fish
The visual appearance of the fish’s head and tail can be used to identify its freshness. A segmentation method that can well isolate those certain parts from a fish body is required for further
Improved YOLOv5 Network Model and Application in Safety Helmet Detection
TLDR
Improvement based on YOLOv5, added a functionality detection scale to allow it to get smaller targets, and introduced the DloU-NMS instead of NMS, which considers the overlap area and the center distance of the two boxes, making it more accurate in suppressing the predicted bounding box.
Visual Servoing of Unknown Objects for Family Service Robots
TLDR
Experimental results show that the proposed robot visual servoing scheme can effectively position an unknown object in complex natural scenes, such as occlusion and illumination changes, and has an excellent positioning accuracy within 0.05 mm positioning error.
A two-level computer vision-based information processing method for improving the performance of human–machine interaction-aided applications
TLDR
A two-level visual information processing (2LVIP) method is introduced to meet the reliability requirements of HMI applications and achieves higher information gain and smaller error under different classification instances compared with conventional methods.
...
...

References

SHOWING 1-10 OF 38 REFERENCES
Deep Learning Architectures for Object Detection and Classification
TLDR
This chapter provides detailed overview on how CNN works and how it is useful in object detection and classification task, and popular deep networks based on CNN like ResNet, VGG16, V GG19, GoogleNet and MobileNet are explained in detail.
You Only Look Once: Unified, Real-Time Object Detection
TLDR
Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Rapid object detection using a boosted cascade of simple features
  • Paul A. Viola, Michael J. Jones
  • Computer Science
    Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
  • 2001
TLDR
A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.
YOLO9000: Better, Faster, Stronger
TLDR
YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories, is introduced and a method to jointly train on object detection and classification is proposed, both novel and drawn from prior work.
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
Accurate Single Stage Detector Using Recurrent Rolling Convolution
TLDR
A novel single stage end-to-end trainable object detection network is proposed by introducing Recurrent Rolling Convolution (RRC) architecture over multi-scale feature maps to construct object classifiers and bounding box regressors which are deep in context.
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
HybridNet: A fast vehicle detection system for autonomous driving
  • Xuerui Dai
  • Computer Science
    Signal Process. Image Commun.
  • 2019
An Object Detection by using Adaptive Structural Learning of Deep Belief Network
TLDR
A new object detection method for the DBN architecture is proposed for localization and category of objects and showed higher performance for both classification and detection than the other CNN methods.
...
...