A Survey on Various Available Object Detection Models and Application In Automatic License Plate Detection

With the development in technologies right from serial to parallel computing, GPU, AI, and deep learning models a series of tools to process complex images have been developed. The main focus of this research is to compare various algorithms(pre-trained models) and their contributions to process complex images in terms of performance, accuracy, time, and their limitations. The pre-trained models we are using are CNN, R-CNN, R-FCN, and YOLO. These models are python language-based and use libraries like TensorFlow, OpenCV, and free image databases (Microsoft COCO and PAS-CAL VOC 2007/2012). These not only aim at object detection but also on building bounding boxes around appropriate locations. Thus, by this review, we get a better vision of these models and their performance and a good idea of which models are ideal for various situations.

Download Full-text

Deep learning for small object detection in images

10.32469/10355/79470 ◽

2020 ◽

Author(s):

◽

Yang Liu

Keyword(s):

Deep Learning ◽

Object Detection ◽

State Of The Art ◽

Aerial Imagery ◽

Small Object ◽

Learning Models ◽

Learning Methods ◽

Bounding Boxes ◽

Small Object Detection ◽

Instance Segmentation

[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] With the rapid development of deep learning in computer vision, especially deep convolutional neural networks (CNNs), significant advances have been made in recent years on object recognition and detection in images. Highly accurate detection results have been achieved for large objects, whereas detection accuracy on small objects remains to be low. This dissertation focuses on investigating deep learning methods for small object detection in images and proposing new methods with improved performance. First, we conducted a comprehensive review of existing deep learning methods for small object detections, in which we summarized and categorized major techniques and models, identified major challenges, and listed some future research directions. Existing techniques were categorized into using contextual information, combining multiple feature maps, creating sufficient positive examples, and balancing foreground and background examples. Methods developed in four related areas, generic object detection, face detection, object detection in aerial imagery, and segmentation, were summarized and compared. In addition, the performances of several leading deep learning methods for small object detection, including YOLOv3, Faster R-CNN, and SSD, were evaluated based on three large benchmark image datasets of small objects. Experimental results showed that Faster R-CNN performed the best, while YOLOv3 was a close second. Furthermore, a new deep learning method, called Retina-context Net, was proposed and outperformed state-of-the art one-stage deep learning models, including SSD, YOLOv3 and RetinaNet, on the COCO and SUN benchmark datasets. Secondly, we created a new dataset for bird detection, called Little Birds in Aerial Imagery (LBAI), from real-life aerial imagery. LBAI contains birds with sizes ranging from 10 by 10 pixels to 40 by 40 pixels. We adapted and applied several state-of-the-art deep learning models to LBAI, including object detection models such as YOLOv2, SSH, and Tiny Face, and instance segmentation models such as U-Net and Mask R-CNN. Our empirical results illustrated the strength and weakness of these methods, showing that SSH performed the best for easy cases, whereas Tiny Face performed the best for hard cases with cluttered backgrounds. Among small instance segmentation methods, U-Net achieved slightly better performance than Mask R-CNN. Thirdly, we proposed a new graph neural network-based object detection algorithm, called GODM, to take the spatial information of candidate objects into consideration in small object detection. Instead of detecting small objects independently as the existing deep learning methods do, GODM treats the candidate bounding boxes generated by existing object detectors as nodes and creates edges based on the spatial or semantic relationship between the candidate bounding boxes. GODM contains four major components: node feature generation, graph generation, node class labelling, and graph convolutional neural network model. Several graph generation methods were proposed. Experimental results on the LBDA dataset show that GODM outperformed existing state-of-the-art object detector Faster R-CNN significantly, up to 12% better in accuracy. Finally, we proposed a new computer vision-based grass analysis using machine learning. To deal with the variation of lighting condition, a two-stage segmentation strategy is proposed for grass coverage computation based on a blackboard background. On a real world dataset we collected from natural environments, the proposed method was robust to varying environments, lighting, and colors. For grass detection and coverage computation, the error rate was just 3%.

Download Full-text

Predicted Anchor Region Proposal with Balanced Feature Pyramid for License Plate Detection in Traffic Scene Images

Complexity ◽

10.1155/2020/5137056 ◽

2020 ◽

Vol 2020 ◽

pp. 1-11

Author(s):

Hoanh Nguyen

Keyword(s):

Deep Learning ◽

Object Detection ◽

Intelligent Transportation Systems ◽

Region Of Interest ◽

Transportation Systems ◽

License Plate ◽

Feature Maps ◽

Feature Pyramid ◽

License Plate Detection ◽

General Object

License plate detection is a key problem in intelligent transportation systems. Recently, many deep learning-based networks have been proposed and achieved incredible success in general object detection, such as faster R-CNN, SSD, and R-FCN. However, directly applying these deep general object detection networks on license plate detection without modifying may not achieve good enough performance. This paper proposes a novel deep learning-based framework for license plate detection in traffic scene images based on predicted anchor region proposal and balanced feature pyramid. In the proposed framework, ResNet-34 architecture is first adopted for generating the base convolution feature maps. A balanced feature pyramid generation module is then used to generate balanced feature pyramid, of which each feature level obtains equal information from other feature levels. Furthermore, this paper designs a multiscale region proposal network with a novel predicted location anchor scheme to generate high-quality proposals. Finally, a detection network which includes a region of interest pooling layer and fully connected layers is adopted to further classify and regress the coordinates of detected license plates. Experimental results on public datasets show that the proposed approach achieves better detection performance compared with other state-of-the-art methods on license plate detection.

Download Full-text

U-Infuse: Democratization of Customizable Deep Learning for Object Detection

Sensors ◽

10.3390/s21082611 ◽

2021 ◽

Vol 21 (8) ◽

pp. 2611

Author(s):

Andrew Shepley ◽

Greg Falzon ◽

Christopher Lawson ◽

Paul Meek ◽

Paul Kwan

Keyword(s):

Deep Learning ◽

Intellectual Property ◽

Object Detection ◽

Image Data ◽

Learning Technologies ◽

Training Data ◽

Learning Models ◽

Ecological Data ◽

Single Class ◽

Large Numbers

Image data is one of the primary sources of ecological data used in biodiversity conservation and management worldwide. However, classifying and interpreting large numbers of images is time and resource expensive, particularly in the context of camera trapping. Deep learning models have been used to achieve this task but are often not suited to specific applications due to their inability to generalise to new environments and inconsistent performance. Models need to be developed for specific species cohorts and environments, but the technical skills required to achieve this are a key barrier to the accessibility of this technology to ecologists. Thus, there is a strong need to democratize access to deep learning technologies by providing an easy-to-use software application allowing non-technical users to train custom object detectors. U-Infuse addresses this issue by providing ecologists with the ability to train customised models using publicly available images and/or their own images without specific technical expertise. Auto-annotation and annotation editing functionalities minimize the constraints of manually annotating and pre-processing large numbers of images. U-Infuse is a free and open-source software solution that supports both multiclass and single class training and object detection, allowing ecologists to access deep learning technologies usually only available to computer scientists, on their own device, customised for their application, without sharing intellectual property or sensitive data. It provides ecological practitioners with the ability to (i) easily achieve object detection within a user-friendly GUI, generating a species distribution report, and other useful statistics, (ii) custom train deep learning models using publicly available and custom training data, (iii) achieve supervised auto-annotation of images for further training, with the benefit of editing annotations to ensure quality datasets. Broad adoption of U-Infuse by ecological practitioners will improve ecological image analysis and processing by allowing significantly more image data to be processed with minimal expenditure of time and resources, particularly for camera trap images. Ease of training and use of transfer learning means domain-specific models can be trained rapidly, and frequently updated without the need for computer science expertise, or data sharing, protecting intellectual property and privacy.

Download Full-text

Introducing AIDE: a Software Suite for Annotating Images with Deep and Active Learning Assistance

10.5194/egusphere-egu21-12065 ◽

2021 ◽

Author(s):

Benjamin Kellenberger ◽

Devis Tuia ◽

Dan Morris

Keyword(s):

Deep Learning ◽

Active Learning ◽

Expert Knowledge ◽

Semantic Segmentation ◽

Third Party ◽

Learning Models ◽

Web Browser ◽

Web Based ◽

Model Training ◽

Bounding Boxes

Ecological research like wildlife censuses increasingly relies on data on the scale of Terabytes. For example, modern camera trap datasets contain millions of images that require prohibitive amounts of manual labour to be annotated with species, bounding boxes, and the like. Machine learning, especially deep learning [3], could greatly accelerate this task through automated predictions, but involves expansive coding and expert knowledge.In this abstract we present AIDE, the Annotation Interface for Data-driven Ecology [2]. In a first instance, AIDE is a web-based annotation suite for image labelling with support for concurrent access and scalability, up to the cloud. In a second instance, it tightly integrates deep learning models into the annotation process through active learning [7], where models learn from user-provided labels and in turn select the most relevant images for review from the large pool of unlabelled ones (Fig. 1). The result is a system where users only need to label what is required, which saves time and decreases errors due to fatigue.<img src="https://contentmanager.copernicus.org/fileStorageProxy.php?f=gnp.0402be60f60062057601161/sdaolpUECMynit/12UGE&app=m&a=0&c=131251398e575ac9974634bd0861fadc&ct=x&pn=gnp.elif&d=1" alt="">Fig. 1: AIDE offers concurrent web image labelling support and uses annotations and deep learning models in an active learning loop.AIDE includes a comprehensive set of built-in models, such as ResNet [1] for image classification, Faster R-CNN [5] and RetinaNet [4] for object detection, and U-Net [6] for semantic segmentation. All models can be customised and used without having to write a single line of code. Furthermore, AIDE accepts any third-party model with minimal implementation requirements. To complete the package, AIDE offers both user annotation and model prediction evaluation, access control, customisable model training, and more, all through the web browser.AIDE is fully open source and available under https://github.com/microsoft/aerial_wildlife_detection.&#160;References

Download Full-text

WORKFLOWFOR TRAINING AND SERVING DEEP LEARNING MODELS FOR IMAGE CLASSIFICATION AND OBJECT DETECTION - APPLICATION TO FAULT DETECTION ON ELECTRIC POLES

10.1049/icp.2021.1557 ◽

2021 ◽

Author(s):

C. Coello ◽

R. Sanchez ◽

S. de Lange ◽

J. Halvorsen ◽

M. Bertani-Økland ◽

...

Keyword(s):

Deep Learning ◽

Fault Detection ◽

Object Detection ◽

Image Classification ◽

Learning Models

Download Full-text

Train Deep Learning Models using subsurface geological images datasets

10.5194/egusphere-egu21-6385 ◽

2021 ◽

Author(s):

Ramy Abdallah ◽

Clare E. Bond ◽

Robert W.H. Butler

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Networks ◽

Learning Models ◽

Structural Interpretation ◽

Performance Accuracy ◽

Learning Techniques ◽

Machine Learning Models

Machine learning is being presented as a new solution for a wide range of geoscience problems. Primarily machine learning has been used for 3D seismic data processing, seismic facies analysis and well log data correlation. The rapid development in technology with open-source artificial intelligence libraries and the accessibility of affordable computer graphics processing units (GPU) makes the application of machine learning in geosciences increasingly tractable. However, the application of artificial intelligence in structural interpretation workflows of subsurface datasets is still ambiguous. This study aims to use machine learning techniques to classify images of folds and fold-thrust structures. Here we show that convolutional neural networks (CNNs) as supervised deep learning techniques provide excellent algorithms to discriminate between geological image datasets. Four different datasets of images have been used to train and test the machine learning models. These four datasets are a seismic character dataset with five classes (faults, folds, salt, flat layers and basement), folds types with three classes (buckle, chevron and conjugate), fault types with three classes (normal, reverse and thrust) and fold-thrust geometries with three classes (fault bend fold, fault propagation fold and detachment fold). These image datasets are used to investigate three machine learning models. One Feedforward linear neural network model and two convolutional neural networks models (Convolution 2d layer transforms sequential model and Residual block model (ResNet with 9, 34, and 50 layers)). Validation and testing datasets forms a critical part of testing the model&#8217;s performance accuracy. The ResNet model records the highest performance accuracy score, of the machine learning models tested. Our CNN image classification model analysis provides a framework for applying machine learning to increase structural interpretation efficiency, and shows that CNN classification models can be applied effectively to geoscience problems. The study provides a starting point to apply unsupervised machine learning approaches to sub-surface structural interpretation workflows.

Download Full-text