A Survey of Deep Learning-based Object Detection

Abstract

Object detection is one of the most important and challenging branches of computer vision, which has been widely applied in peoples life, such as monitoring security, autonomous driving and so on, with the purpose of locating instances of semantic objects of a certain class. With the rapid development of deep learning networks for detection tasks, the performance of object detectors has been greatly improved. In order to understand the main development status of object detection pipeline, thoroughly and deeply, in this survey, we first analyze the methods of existing typical detection models and describe the benchmark datasets. Afterwards and primarily, we provide a comprehensive overview of a variety of object detection methods in a systematic manner, covering the one-stage and two-stage detectors. Moreover, we list the traditional and new applications. Some representative branches of object detection are analyzed as well. Finally, we discuss the architecture of exploiting these object detection methods to build an effective and efficient system and point out a set of development trends to better follow the state-of-the-art algorithms and further research.

30 pages,12 figures

References in corpus (81)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• YOLOv3: An Incremental Improvement
• DeepPose: Human Pose Estimation via Deep Neural Networks
• DSSD : Deconvolutional Single Shot Detector
• UnitBox: An Advanced Object Detection Network
• A Survey on Object Detection in Optical Remote Sensing Images
• Arbitrary-Oriented Scene Text Detection via Rotation Proposals
• Fine-Grained Visual Classification of Aircraft
• Deep Face Recognition: A Survey
• Richer Convolutional Features for Edge Detection
• Multiple Object Recognition with Visual Attention
• Video Salient Object Detection via Fully Convolutional Networks
• A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector
• NormFace: L2 Hypersphere Embedding for Face Verification
• T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
• Learning multiple visual domains with residual adapters
• Object Detection in 20 Years: A Survey
• Human pose estimation via Convolutional Part Heatmap Regression
• Change-Point Detection in Time-Series Data by Relative Density-Ratio Estimation
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network
• The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
• FSSD: Feature Fusion Single Shot Multibox Detector
• Vision Meets Drones: A Challenge
• Beyond Skip Connections: Top-Down Modulation for Object Detection
• Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations
• The EuroCity Persons Dataset: A Novel Benchmark for Object Detection
• LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images
• Light-Head R-CNN: In Defense of Two-Stage Object Detector
• Object Detection from Video Tubelets with Convolutional Neural Networks
• L2-constrained Softmax Loss for Discriminative Face Verification
• Direction-aware Spatial Context Features for Shadow Detection and Removal
• R${}^2$-CNN: Fast Tiny Object Detection in Large-Scale Remote Sensing Images
• DetNet: A Backbone network for Object Detection
• Deep Learning for Generic Object Detection: A Survey
• Scene Text Detection via Holistic, Multi-Channel Prediction
• Deformable ConvNets v2: More Deformable, Better Results
• Vehicle Instance Segmentation from Aerial Image and Video Using a Multi-Task Learning Residual Fully Convolutional Network
• CenterNet: Keypoint Triplets for Object Detection
• CornerNet-Lite: Efficient Keypoint Based Object Detection
• Object Detection in Videos with Tubelet Proposal Networks
• Seq-NMS for Video Object Detection
• Face Attention Network: An Effective Face Detector for the Occluded Faces
• Libra R-CNN: Towards Balanced Learning for Object Detection
• Towards Accurate One-Stage Object Detection with AP-Loss
• R${}^3$-Net: A Deep Network for Multi-oriented Vehicle Detection in Aerial Images and Videos
• Universal representations:The missing link between faces, text, planktons, and cat breeds
• Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detection
• Rethinking Feature Discrimination and Polymerization for Large-scale Recognition
• Buildings Detection in VHR SAR Images Using Fully Convolution Neural Networks
• Rethinking on Multi-Stage Networks for Human Pose Estimation
• Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
• Contrastive Adaptation Network for Unsupervised Domain Adaptation
• Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
• Fast Fine-grained Image Classification via Weakly Supervised Discriminative Localization
• Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network
• MDSSD: Multi-scale Deconvolutional Single Shot Detector for Small Objects
• Stack-Captioning: Coarse-to-Fine Learning for Image Captioning
• Region Proposal by Guided Anchoring
• Tiny SSD: A Tiny Single-shot Detection Deep Convolutional Neural Network for Real-time Embedded Object Detection
• Fine-grained Discriminative Localization via Saliency-guided Faster R-CNN
• Bi-Directional Cascade Network for Perceptual Edge Detection
• C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
• Improving Object Detection from Scratch via Gated Feature Reuse
• AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations
• Attention Based Glaucoma Detection: A Large-scale Database and CNN Model
• Attentional Network for Visual Object Detection
• Improving Text Proposals for Scene Images with Fully Convolutional Networks
• Towards Universal Object Detection by Domain Attention
• ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving
• Weaving Multi-scale Context for Single Shot Detector
• Wide-Residual-Inception Networks for Real-time Object Detection
• DuBox: No-Prior Box Objection Detection via Residual Dual Scale Detectors
• Less is More: Learning Highlight Detection from Video Duration
• Activity Driven Weakly Supervised Object Detection
• Object Detection based on Region Decomposition and Assembly
• A Simple Pooling-Based Design for Real-Time Salient Object Detection
• Object Detection from Scratch with Deep Supervision

Cited by in corpus (58)

• 3D Object Detection for Autonomous Driving: A Survey
• Medical Deep Learning -- A systematic Meta-Review
• A comprehensive review of Binary Neural Network
• A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects
• Aerial Images Processing for Car Detection using Convolutional Neural Networks: Comparison between Faster R-CNN and YoloV3
• LittleYOLO-SPP: A Delicate Real-Time Vehicle Detection Algorithm
• Segmentation of cell-level anomalies in electroluminescence images of photovoltaic modules
• Swin-transformer-yolov5 For Real-time Wine Grape Bunch Detection
• IDDA: a large-scale multi-domain dataset for autonomous driving
• Continuous Human Action Recognition for Human-Machine Interaction: A Review
• Computer Vision with Deep Learning for Plant Phenotyping in Agriculture: A Survey
• Enhancing Object Detection for Autonomous Driving by Optimizing Anchor Generation and Addressing Class Imbalance
• On-Device Machine Learning: An Algorithms and Learning Theory Perspective
• Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies
• Motion Generation Using Bilateral Control-Based Imitation Learning with Autoregressive Learning
• Generation of microbial colonies dataset with deep learning style transfer
• Collaborative Multi-Robot Systems for Search and Rescue: Coordination and Perception
• On Model Calibration for Long-Tailed Object Detection and Instance Segmentation
• Effect of Annotation Errors on Drone Detection with YOLOv3
• FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagery
• Model-agnostic explainable artificial intelligence for object detection in image data
• Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems
• Machine Learning Based Analysis of Finnish World War II Photographers
• LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood
• HRNET: AI on Edge for mask detection and social distancing
• Evaluating Object (mis)Detection from a Safety and Reliability Perspective: Discussion and Measures
• An Analysis of Deep Object Detectors For Diver Detection
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• MAT-Fly: An Educational Platform for Simulating Unmanned Aerial Vehicles Aimed to Detect and Track Moving Objects
• Cascaded Structure Tensor Framework for Robust Identification of Heavily Occluded Baggage Items from Multi-Vendor X-ray Scans
• How to Track and Segment Fish without Human Annotations: A Self-Supervised Deep Learning Approach
• SniffyArt: The Dataset of Smelling Persons
• Sensitivity - Local Index to Control Chaoticity or Gradient Globally -
• Vision-Based Assistive Technologies for People with Cerebral Visual Impairment: A Review and Focus Study
• Gravity Network for end-to-end small lesion detection
• Towards large-scale, automated, accurate detection of CCTV camera objects using computer vision. Applications and implications for privacy, safety, and cybersecurity. (Preprint)
• Towards Sensor Data Abstraction of Autonomous Vehicle Perception Systems
• Battery detection of XRay images using transfer learning
• A Robust Pedestrian Detection Approach for Autonomous Vehicles
• A Real Time 1280x720 Object Detection Chip With 585MB/s Memory Traffic
• Renormalized Connection for Scale-preferred Object Detection in Satellite Imagery
• Human-in-the-loop Reasoning For Traffic Sign Detection: Collaborative Approach Yolo With Video-llava
• TYolov5: A Temporal Yolov5 Detector Based on Quasi-Recurrent Neural Networks for Real-Time Handgun Detection in Video
• Marine vessel tracking using a monocular camera
• Tuning a variational autoencoder for data accountability problem in the Mars Science Laboratory ground data system
• Utilizing dataset affinity prediction in object detection to assess training data
• Transfer Learning Approach for Railway Technical Map (RTM) Component Identification
• Fast Person Detection Using YOLOX With AI Accelerator For Train Station Safety
• Non-invasive hemodynamic analysis for aortic regurgitation using computational fluid dynamics and deep learning
• Pulmonary embolism identification in computerized tomography pulmonary angiography scans with deep learning technologies in COVID-19 patients
• SISA: Securing Images by Selective Alteration
• Deep Learning -- A first Meta-Survey of selected Reviews across Scientific Disciplines, their Commonalities, Challenges and Research Impact
• Multiple Myeloma Cancer Cell Instance Segmentation
• Issues in Object Detection in Videos using Common Single-Image CNNs
• Compressed Object Detection
• A Study on Trees's Knots Prediction from their Bark Outer-Shape
• Semi-supervised Learning for Dense Object Detection in Retail Scenes
• Object Detection on Single Monocular Images through Canonical Correlation Analysis