Open AccessPosted Content
You Only Look Once: Unified, Real-Time Object Detection
Reads0
Chats0
TLDR
YOLO as discussed by the authors predicts bounding boxes and class probabilities directly from full images in one evaluation, which can be optimized end-to-end directly on detection performance, and achieves state-of-the-art performance.Abstract:
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance.
Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is far less likely to predict false detections where nothing exists. Finally, YOLO learns very general representations of objects. It outperforms all other detection methods, including DPM and R-CNN, by a wide margin when generalizing from natural images to artwork on both the Picasso Dataset and the People-Art Dataset.read more
Citations
More filters
Patent
A vehicle identification matching system based on a vehicle annual inspection mark
TL;DR: In this paper, a vehicle identification matching system based on a vehicle annual inspection mark is presented, which comprises a data module, a YOLO network module, coarse positioning module, PCA dimension reduction processing module, an SIFT further feature extraction module, and an output module.
Journal ArticleDOI
CIMask: Segmenting instances by class-specific semantic feature extraction and instance-specific attribute discrimination
Canqun Xiang,Wenbin Zou,Chen Xu +2 more
TL;DR: This paper presents a novel fast single-stage instance segmentation method, called CIMask, which is faster and more accurate than a few recent competitive approaches, including Mask R-CNN baselines.
Patent
Intelligent edge calculation system of minimally invasive visible image processing
TL;DR: In this paper, an intelligent edge calculation system of minimally invasive visible image processing is proposed to reduce the communication load with the cloud server and calculation load of the Cloud server and meet the endoscope intelligent auxiliary diagnosis in an offline/online state.
Proceedings ArticleDOI
ALeader-following Method Based on Binocular Stereo Vision For Quadruped Robots
TL;DR: This paper presents a leader-following framework by stereo-vision, which allows quadruped robots to adapt to challenging outdoor environments and proposes an improved tracker based on traditional KCF with multi-feature fusion and multi-scale estimation.
Proceedings ArticleDOI
Online Graph Completion: Multivariate Signal Recovery in Computer Vision
TL;DR: This work designs the optimization model in the Fourier domain of the graph describing how ideas based on adaptive submodularity provide algorithms that work well in practice on a large set of images collected from Imgur and shows applications to an experimental design problem in neuroimaging.
References
More filters
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Journal ArticleDOI
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
Posted Content
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TL;DR: Faster R-CNN as discussed by the authors proposes a Region Proposal Network (RPN) to generate high-quality region proposals, which are used by Fast R-NN for detection.
Proceedings ArticleDOI
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
Proceedings ArticleDOI
Object recognition from local scale-invariant features
TL;DR: Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.