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
Object identification method and system for sweeping robot
TL;DR: In this article, an object identification method for a sweeping robot is presented, which comprises the steps that an object detection model acquired through depth learning in advance is transplanted to an embedded platform of the robot; image information around the robot is collected; a collected image is preprocessed; the pre-processed image is input to the object identification model, object information existing in the input image is calculated, and an object in the image is identified.
Proceedings ArticleDOI
Ship Detection and Segmentation using Unet
TL;DR: The research shows that the modes are robust and can perform well even with difficult backgrounds like clouds, waves etc and the best model archived 0.823 on F2 score at different IOU thresholds on Airbus ship detection challenge test dataset.
Journal ArticleDOI
Gender Recognition via Fused Silhouette Features Based on Visual Sensors
TL;DR: A new subGEI map is introduced by calculating from fewer frames than a gait cycle, extract the synthetic optical flow of multi subGEIs as temporal features, and utilize a two-stream CNN to combine use the GEI and the optical flow information for further gait analysis.
Posted Content
G-CNN: an Iterative Grid Based Object Detector
TL;DR: G-CNN as mentioned in this paper is an object detection technique based on CNNs which works without proposal algorithms and uses a multi-scale grid of fixed bounding boxes to detect the objects.
Proceedings ArticleDOI
Adaptive Binary-Ternary Quantization
TL;DR: In this article, the authors proposed an adaptive combination of binary and ternary quantization, namely Smart Quantization (SQ), in which the quantization depth is modified directly via a regularization function, so that the model is trained only once.
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.