DPT: Deformable Patch-based Transformer for Visual Recognition

Traffic violation apprehension is one of the traffic problems here in the Philippines. One example is the No Helmet No Ride Law that is implemented but many motorists still choose to ignore. To alleviate the problem the government has offered many solutions, one of which is the No Contact Traffic Apprehension Policy that uses CCTV Monitoring. To further enhance this solution the government has partnered with the De La Salle University to use artificial intelligence in the system. Computer Vision tasks like image classification and object detection can help automate the traffic apprehension system. Image classification and object detection are technologies which are used in computer vision in defining an image or coordinates of an object in an image. In this work, a novel approach to classifying motorcycle riders between wearing a helmet or not will be developed. It will be demonstrated using deep machine learning, specifically convolutional neural network and by utilizing different pre-trained models to a gathered dataset.

Computer vision (CV) is a subfield of artificial intelligence (AI) that trains computers to understand our visual world based on digital images. There are many successful applications of CV including face and hand gesture detection, weather recording, smart farming, and self-driving cars. Recent advances in computer vision with machine learning (ML) provide a new avenue for microbiological analysis. ML has been proven efficient and precise due to its automatic analysis of the geometric features and texture of organisms in optical microscopy images. This work describes a workshop that teaches basics of CV using ML (image classification, object detection) using Python notebook examples in Google Colab and Jetson Nano. The workshop is designed for senior undergraduate or beginning graduate chemistry students who would like to learn how to classify and detect microorganisms such as amoebae. The workshop content includes three sections: image classification with convolutional neutral netowork (CNN) in Google Colab, object detection with Mask R-CNN in Google Colab, and object detection with SSD-mobilenet in Jetson Nano.

We propose Real Full Binary Neural Network (RFBNN), a method that can reduce the memory and compute power of Deep Neural Networks. This method has similar performance to other BNNs in image classification and object detection, while reducing computation power and memory size. In RFBNN, the weight filters are approximated as a binary value by applying a sign function; we apply real binary weight to the whole layer. Therefore, RFBNN can be efficiently implemented on CPU, FPGA and GPU. Results of the all experiments show that the proposed method works successfully on various task such as image classification and object detection. All layers in our networks are composed of only {1, −1}, and unlike the other BNN, there is no scaling factor. Compared to recent network binarization methods, BC, BWN and BWRN, we have reduced the memory size and computation costs, but the performance is the same or better.

Review on self-supervised image recognition using deep neural networks

Tuberculosis (TB) is a contagious disease affecting millions of people annually worldwide. Treatment of this disease and reduction in local epidemics can be improved markedly by increasing the speed and efficiency of screening and diagnosis. eRxNet is a pipeline of convolutional neural networks designed to provide healthcare professionals with detailed and accurate analysis of chest X-rays (CXRs) for TB screening. The pipeline combines whole image classification, object detection (bounding boxes), and instance segmentation (polygonal masks) to provide data analysis at varying levels of detail. In order to construct a high performing system, a comparison of different CNN architectures applied to these tasks is presented. Images from two large TB datasets, UML-Peru and TBX11K, were used for training and evaluation of the models. Combining the two datasets required the development of a preprocessing stage which includes lung segmentation and image enhancement. We show that the resulting four stage pipeline of CNNs, using a combination of DenseNet, Faster R-CNN, and Mask R-CNN, has sufficiently strong performance to be a useful tool for TB screening.

This research explores the fusion of computer vision and agricultural quality control. It investigates the efficacy of computer vision algorithms, particularly in image classification and object detection, for non-destructive assessment. These algorithms offer objective, rapid, and error-resistant analysis compared to human inspection. The study provides an extensive overview of using computer vision to evaluate grain and fertilizer granule quality, highlighting granule size's significance. It assesses prevailing object detection methods, outlining their advantages and drawbacks. The paper identifies the prevailing trend of framing quality inspection as an image classification challenge and suggests future research directions. These involve exploring object detection, image segmentation, or hybrid models to enhance fertilizer granule quality assessment.

In computer vision, significant advances have been made in recent years on object recognition and detection with the rapid development of deep learning, especially deep convolutional neural networks (CNN). The majority of deep learning methods for object detection have been developed for large objects and their performances on small-object detection are not very good. This paper contributes to research in low-resolution small-object detection by evaluating the performances of leading deep learning methods for object detection using a common dataset, which is a new dataset for bird detection, called Little Birds in Aerial Imagery (LBAI), created from real-life aerial imagery data. LBAI contains birds with sizes ranging from 10px to 40px. In our experiments, some of the best deep learning architectures were implemented and applied to LBAI, which include object detection techniques such as YOLOv2, SSH, and Tiny Face, in addition to small instance segmentation techniques including U-Net and Mask R-CNN. Among the object detection methods, experimental results demonstrated that SSH performed the best for easy cases, whereas Tiny Face performed the best for hard cases, i.e. where a cluttered background makes detecting birds difficult. Among small instance segmentation methods, experimental results revealed U-Net achieved slightly better performance than Mask R-CNN.

The objective of this paper is to build an Object Recognition model using ‘TINY YOLO’ and FPGA. Object Recognition is a CV (i. e., Computer Vision) technique for identifying and detecting objects in images or videos. Object recognition is a key output of DL (i. e., Deep Learning) and ML (i. e., Machine Learning). When we humans look at an image or video, we can readily spot people, object, scene and visual details. The aim of this is to teach a computer to do what comes innately to a human being. Object recognition is done with Image Classification, Object Localization and Object Detection that combines these two tasks and localizes and classifies an object in an image. Object Recognition has become a pivotal technology for driverless cars, security purpose, traffic surveillance etc., It is also used in a various application such as disease detection in bio imaging, industrial examination, and robotic vision. Hence, in a nutshell, ‘Object Recognition is the staple of automation industry’.

Computer vision is an essential field of artificial intelligence (AI). Under the scope of this field, the software is made to perceive the data through cameras, pictures, and videos. Although computers do not have a biological vision of their own, they are still very capable of processing an image by themselves. Under the scope of computer vision, numeric values are used as features to train machine learning models that can make actual predictions about an image and its contents. Scientists often use a combination of machine learning models and PaaS solutions, such as the cognitive services offered by Microsoft Azure, to bridge the gap between what a person sees and what a computer can do with it. The beginning of the chapter gives an overview of Azure Cognitive Services and why you should use them. In this section, you will learn about Azure Cognitive Services such as speech, language, vision, decision, and the OpenAI service. Following that, you will learn about computer vision and its key components, such as image classification and object detection. Following that, you will learn about the various computer vision applications and services that Azure supports, such as computer vision, custom vision, and face and form recognizers.

Purpose This study aims to automate the visual inspection of piling sheets in water channel construction using artificial intelligence (AI). By employing image classification and object detection techniques, the research focuses on extracting and analysing geometric features to enhance the accuracy and efficiency of the inspection process. It also addresses key challenges associated with the unique characteristics of construction materials and the limited variability of available inspection datasets. Design/methodology/approach Convolutional neural networks (CNNs) with varying complexities are employed for image classification, across four and six classes, and for object detection of piling sheets in water channel environments. A dataset provided by Witteveen + Bos is preprocessed to generate training sets, and the CNN architectures are optimized for enhanced performance. The accuracy and efficiency of the proposed models are evaluated and compared against traditional manual inspection methods. Findings The AI-driven approach significantly reduces processing time, evaluating 40,000 images in just 11.9 h, compared to approximately one month using manual assessment. The 4-class classification model achieves an accuracy of 96%, while the 6-class model attains 72%. The object detection model produces a mean average precision (mAP) of 79%. These results meet the performance standards set by the Dutch company Witteveen + Bos, which demonstrate the effectiveness of AI in automating the inspection of piling sheets. Originality/value This study introduces a novel AI-based approach for assessing piling sheets, demonstrating substantial improvements over traditional inspection methods. It introduces a systematic evaluation of various CNN architectures and hyperparameters to optimize the models specifically for piling sheet inspection rather than relying on off-the-shelf solutions. The use of CNNs for both image classification and object detection adheres to relevant Dutch engineering standards. Notably, the reduction in processing time, from one month to around 12 h, represents a major advancement in the efficiency of civil engineering inspections.

Efficient and adaptive computer vision systems have been proposed to make computer vision tasks, such as image classification and object detection, optimized for embedded or mobile devices. These solutions, quite recent in their origin, focus on optimizing the model (a deep neural network) or the system by designing an adaptive system with approximation knobs. Despite several recent efforts, we show that existing solutions suffer from two major drawbacks. First , while mobile devices or systems-on-chips usually come with limited resources including battery power, most systems do not consider the energy consumption of the models during inference. Second , they do not consider the interplay between the three metrics of interest in their configurations, namely, latency, accuracy, and energy. In this work, we propose an efficient and adaptive video object detection system— Virtuoso , which is jointly optimized for accuracy, energy efficiency, and latency. Underlying Virtuoso is a multi-branch execution kernel that is capable of running at different operating points in the accuracy-energy-latency axes, and a lightweight runtime scheduler to select the best fit execution branch to satisfy the user requirement. We position this work as a first step in understanding the suitability of various object detection kernels on embedded boards in the accuracy-latency-energy axes, opening the door for further development in solutions customized to embedded systems and for benchmarking such solutions. Virtuoso is able to achieve up to 286 FPS on the NVIDIA Jetson AGX Xavier board, which is up to 45× faster than the baseline EfficientDet D3 and 15× faster than the baseline EfficientDet D0. In addition, we also observe up to 97.2% energy reduction using Virtuoso compared to the baseline YOLO (v3)—a widely used object detector designed for mobiles. To fairly compare with Virtuoso , we benchmark 15 state-of-the-art or widely used protocols, including Faster R-CNN (FRCNN) [NeurIPS’15], YOLO v3 [CVPR’16], SSD [ECCV’16], EfficientDet [CVPR’20], SELSA [ICCV’19], MEGA [CVPR’20], REPP [IROS’20], FastAdapt [EMDL’21], and our in-house adaptive variants of FRCNN+, YOLO+, SSD+, and EfficientDet+ (our variants have enhanced efficiency for mobiles). With this comprehensive benchmark, Virtuoso has shown superiority to all the above protocols, leading the accuracy frontier at every efficiency level on NVIDIA Jetson mobile GPUs. Specifically, Virtuoso has achieved an accuracy of 63.9%, which is more than 10% higher than some of the popular object detection models, FRCNN at 51.1% and YOLO at 49.5%.

Significant advancement of research on image classification and object detection has been achieved in the past decade.Deep convolutional neural networks have exhibited superior performance in many visual recognition tasks including image classification, object detection, and scene labeling, due to their large learning capacity and resistance to overfit.However, learning a robust deep CNN model for object recognition is still quite challenging because image classification and object detection is a severely unbalanced large-scale problem.In this dissertation, we aim at improving the performance of image classification and object detection algorithms by taking advantage of deep convolutional neural networks by utilizing the following strategies: We introduce Deep Neural Pattern, a local feature densely extracted from an image with arbitrary resolution using a well trained deep convolutional neural network.We propose a latent CNN framework, which will automatically select the most discriminate region in the image to reduce the effect of irrelevant regions.We also develop a new combination scheme for multiple CNNs via Latent Model Ensemble to overcome the local minima problem of CNNs.In addition, a weakly supervised CNN framework, referred to as Multiple Instance Learning Convolutional Neural Networks is developed to alleviate strict label requirements.Finally, a novel residual-network architecture, Residual networks of Residual networks, is constructed to improve the optimization ability of very deep convolutional neural networks.All the proposed algorithms are validated by thorough experiments and have shown solid accuracy on large scale object detection and recognition benchmarks.

Geospatial imaging technique has opened a door for researchers to implement multiple beneficial applications in many fields, including military investigation, disaster relief, and urban traffic control. As the resolution of geospatial images has increased in recent years, the detection of geospatial objects has attracted a lot of researchers. Mask R-CNN had been designed to identify an object outlines at the pixel level (instance segmentation), and for object detection in natural images. This study describes the Mask R-CNN model and uses it to detect objects in geospatial images. This experiment was prepared an existing dataset to be suitable with object segmentation, and it shows that Mask R-CNN also has the ability to be used in geospatial object detection and it introduces good results to extract the ten classes dataset of Seg-VHR-10.

Object detection is a hot topic with various applications in computer vision, e.g., image understanding, autonomous driving, and video surveillance. Much of the progresses have been driven by the availability of object detection benchmark datasets, including PASCAL VOC, ImageNet, and MS COCO. However, object detection on the drone platform is still a challenging task, due to various factors such as view point change, occlusion, and scales. To narrow the gap between current object detection performance and the real-world requirements, we organized the Vision Meets Drone (VisDrone2018) Object Detection in Image challenge in conjunction with the 15th European Conference on Computer Vision (ECCV 2018). Specifically, we release a large-scale drone-based dataset, including 8, 599 images (6, 471 for training, 548 for validation, and 1, 580 for testing) with rich annotations, including object bounding boxes, object categories, occlusion, truncation ratios, etc. Featuring a diverse real-world scenarios, the dataset was collected using various drone models, in different scenarios (across 14 different cities spanned over thousands of kilometres), and under various weather and lighting conditions. We mainly focus on ten object categories in object detection, i.e., pedestrian, person, car, van, bus, truck, motor, bicycle, awning-tricycle, and tricycle. Some rarely occurring special vehicles (e.g., machineshop truck, forklift truck, and tanker) are ignored in evaluation. The dataset is extremely challenging due to various factors, including large scale and pose variations, occlusion, and clutter background. We present the evaluation protocol of the VisDrone-DET2018 challenge and the comparison results of 38 detectors on the released dataset, which are publicly available on the challenge website: http://www.aiskyeye.com/. We expect the challenge to largely boost the research and development in object detection in images on drone platforms.

Nowadays Convolutional Neural Networks (CNNs) are being employed in a wide range of industrial technologies for a variety of sectors, such as medical, automotive, aviation, agriculture, space, etc. This paper reviews the state-of-the-art in both the field of CNNs for image classification and object detection and Autonomous Driving Systems (ADSs) in a synergetic way. Layer-based details of CNNs along with parameter and floating-point operation number calculations are outlined. Using an evolutionary approach, the majority of the outstanding image classification CNNs, published in the open literature, is introduced with a focus on their accuracy performance, parameter number, model size, and inference speed, highlighting the progressive developments in convolutional operations. Results of a novel investigation of the convolution types and operations commonly used in CNNs are presented, including a timing analysis aimed at assessing their impact on CNN performance. This extensive experimental study provides new insight into the behaviour of each convolution type in terms of training time, inference time, and layer level decomposition. Building blocks for CNN-based object detection are also discussed, such as backbone networks and baseline types, and then representative state-of-the-art designs are outlined. Experimental results from the literature are summarised for each of the reviewed models. This is followed by an overview of recent ADSs related works and current industry activities, aiming to bridge academic research and industry practice on CNNs and ADSs. Design approaches targeted at solving problems of automakers in achieving real-time implementations are also proposed based on a discussion of design constraints, human vs. machine evaluations and trade-off analysis of accuracy vs. size. Current technologies, promising directions, and expectations from the literature on ADSs are introduced including a comprehensive trade-off analysis from a human-machine perspective.