Object detection through region proposal based techniques

Deep neural networks (DNN’s) have achieved state-of-the-art (SOTA) for many image-related tasks like classification, object detection, etc. The authors have shown that DNN’s can be easily fooled by adversarial examples that can be generated by adding small distortions or perturbations to the images. Several attack methods to add these perturbations in images have been proposed like the Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), etc. to create distortions in images that cause the DNN’s to misclassify instances. It is essential to come up with strategies to identify such fake images. Keeping this in mind, we propose an end-to-end pipeline capable of detecting adversarially attacked images, i.e., images with perturbations. For a given image, we generate images with manipulation masks using Mantra-Net and pass them through a trained binary classifier that distinguishes between perturbed and original images. Experiments on the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2012 dataset have shown that our pipeline achieves an accuracy of 0.986 on the task of detecting adversarially crafted images.

Object detection is a cornerstone task in computer vision, impacting diverse domains from autonomous systems to medical imaging. This study presents a systematic evaluation of three leading detection architecturesFaster Region-based Convolutional Neural Networks (Faster R-CNN), You Only Look Once version 8 (YOLOv8), and Detection Transformer (DETR), with the objective of evaluating their performance characteristics and practical deployment potential. Through comparative experiments, the research evaluates Faster R-CNNs precision (Delivers 76.4% mean Average Precision with a processing speed of 5-7 Frames Per Second (FPS)), YOLOv8s real-time efficiency (53.9% mean Average Precision (mAP) at 80+ FPS), and DETR attention-based innovation (42% AP). Results highlight the strengths and weaknesses of each model: Faster R-CNN excels in accuracy-demanding applications like medical diagnosis, YOLOv8 dominates real-time tasks such as autonomous driving, and DETR offers promising temporal analysis capabilities despite higher computational costs. The study proposes innovative solutions, including cross-scale attention mechanisms and dynamic inference techniques, to address limitations such as small-object detection and edge deployment. The findings provide valuable insights for architecture selection, offering actionable guidelines for industrial implementation and laying the groundwork for future advancements in multimodal fusion and self-supervised learning paradigms. This framework accelerates the development of next-generation detection systems tailored for emerging Artificial Intelligence (AI) applications.

Object Detection has been a great challenge over the years. The reason behind is that, it is applied for numerous real time applications like vision based control, traffic control, video surveillance, sports analysis, etc. But, object detection in a video sequence is a highly challenging task. It has various problems like occlusion, fast moving objects, shadow, poor lighting, color contrast and other static background objects. This reason brought the object detection to be a thrust research area in the field of image processing. In the previous researches the conventional methods of object detection like Frame Difference, Mixture of Gaussian (MoG), Optical Flow etc., still have the above problems. Hence the research focuses on a different approach in object detection using Metaheuristic algorithm for the video sequence of volley ball player in the practice session. In this research three Metaheuristic Algorithms, namely Firefly, Teaching and Learning Based Optimization (TLBO) and Cuckoo Search Algorithm are used. These algorithms are evaluated and compared with the parameters like accuracy, precision, and recall. The result shows Cuckoo Search Algorithm is best suited to object detection especially in this application.

Object detection and recognition is an essential task in computer vision with numerous real-world applications such as surveillance, self-driving cars, and robotics. In recent years, deep learning-based approaches have significantly improved the accuracy and speed of object detection and recognition. The You Only Look Once version 3 (YOLOv3) algorithm is a popular deep learning-based approach that can detect and recognize objects in real-time. The Common Objects in Context (COCO) dataset is a large-scale dataset with over 330,000 labeled images and more than 2.5 million object instances, making it a popular choice for object detection and recognition tasks. In this paper, we propose a deep learning-based approach for real-time object detection and recognition using the YOLOv3 architecture and COCO dataset. We evaluate our approach based on several performance metrics, including mean average precision (mAP), frames per second (FPS), total object detection time, object detection accuracy, false positive rate, number of detected objects, and mean intersection over union (mIoU). Our results show that our approach achieves a mean average precision of 0.76 on the COCO dataset and a real-time performance of 40 frames per second on a single GPU. Additionally, our approach achieves an object detection accuracy of 93.5%, a false positive rate of 6.5%, and a mean intersection over union of 0.65. Our proposed approach shows promising results for real-time object detection and recognition and can be applied to various real-world applications.

Background:Automatic detection of surgical instruments is essential for artificial intelligence surgery. This study aimed to construct a large-scale dataset of gynecological laparoscopic surgical instruments based on real surgical scenarios, achieve high-precision real-time detection of surgical instruments, and explore their potential application in surgical skill evaluation.Materials and methods:This cross-sectional study collected 265 gynecological laparoscopic surgical videos from two medical centers for instrument detection. Videos were divided into training and testing sets in a 4:1 ratio, with 161 348 instrument instances extracted. The instruments were detected using Real-Time Models for Object Detection (RTMDet). The mean average precision, sensitivity, and F1 score served as evaluation metrics. External validation was conducted on an independent dataset from a third medical center. Additionally, we further compared the RTMDet with the state-of-the-art PP-YOLOE model on the same dataset. Furthermore, this study performed real-time tracking of instruments during the vaginal cuff suturing step of laparoscopic hysterectomy and compared the differences in kinematic data between proficient and non-proficient videos.Results:The mean average precision, sensitivity, and F1 score for nine types of surgical instruments were 91.75%, 94.29%, and 93.00%, respectively. External validation on the independent dataset demonstrated robust performance. In the comparison with PP-YOLOE, RTMDet demonstrated superior performance in all metrics. In the comparative analysis of kinematic data, the proficient group demonstrated significantly lesser path lengths and inter-quartile range, shorter moving times, and higher movement velocities for instruments used by both hands compared to the non-proficient group.Conclusions:This study established a large-scale, real scenario-based database of gynecological laparoscopic instruments. Using the RTMDet model, high-precision real-time detection and tracking of multiple instruments were achieved. Furthermore, this study identified several instrument kinematic metrics that can be used for surgical skill assessment, providing a reference for the objective quantification of the subjective Global Operative Assessment of Laparoscopic Skills.

The object detection approaches in conjunction with Fast/Faster R-CNN and YOLO have shown the benchmarking performance on several occasions. Inspired by the Refine Net, we propose a new model called Faster+ R-CNN based on Faster R-CNN, which is mainly based on iterative refinement on the proposed regions. The Faster+ R-CNN model can iteratively refine the region proposal based on previous output. We trained and tested our new model on PASCAL VOC 2007 dataset, and experiments showed that our method can iteratively improve the mean average precision (mAP) from 0.6702 to 0.6764 in object detecting task. We also demonstrate the facial detection results using the Faster+ R-CNN on the widely used Face Detection Dataset and Benchmark (FDDB) benchmark. By training the Faster+ R-CNN model on the large scale WIDER face dataset, we report the improved results on two widely used face detection benchmarks including FDDB.

Withcontinuous advancements in remote sensing technology, object detection in remote sensing images has emerged as a critical research direction in maritime surveillance, port management, and national defense. Among these applications, ship detection is a key task. Due to the fact that ships in images typically exhibit arbitrary rotations, multi-scale distributions, and complex backgrounds, conventional detection methods based on horizontal or rotated bounding boxes often fail to adequately capture the fine-grained information of the targets, thereby compromising detection accuracy. This paper proposes the Dense Representative Points-Guided Rotated-Ship Detection (DenseRRSD) method. The proposed approach represents ship objects using dense representative points (RepPoints) to effectively capture local semantic information, thereby avoiding the background noise issues associated with traditional rectangular bounding box representations. To further enhance detection accuracy, an edge region sampling strategy is devised to uniformly sample RepPoints from critical ship parts, and a Weighted Residual Feature Pyramid Network (WRFPN) is introduced to efficiently fuse the multi-scale features through residual connections and learnable weights. In addition, a Weighted Chamfer Loss (WCL) combined with a staged localization loss strategy is employed to progressively refine localization from coarse to fine stages. Experimental results on both the HRSC2016 dataset and the newly constructed DOTA-SHIP dataset demonstrate that DenseRRSD achieves state-of-the-art detection accuracy, with mean Average Precision (mAP) scores of 91.2% and 83.2%, respectively, significantly outperforming existing methods. These results verify the effectiveness and robustness of the proposed approach in rotated-ship detection under diverse conditions.

Recent advances in the field of object detection and face recognition have made it possible to develop practical video surveillance systems with embedded object detection and face recognition functionalities that are accurate and fast enough for commercial uses. In this paper, we compare some of the latest approaches to object detection and face recognition and provide reasons why they may or may not be amongst the best to be used in video surveillance applications in terms of both accuracy and speed. It is discovered that Faster R-CNN with Inception ResNet V2 is able to achieve some of the best accuracies while maintaining real-time rates. Single Shot Detector (SSD) with MobileNet, on the other hand, is incredibly fast and still accurate enough for most applications. As for face recognition, FaceNet with Multi-task Cascaded Convolutional Networks (MTCNN) achieves higher accuracy than advances such as DeepFace and DeepID2+ while being faster. An end-to-end video surveillance system is also proposed which could be used as a starting point for more complex systems. Various experiments have also been attempted on trained models with observations explained in detail. We finish by discussing video object detection and video salient object detection approaches which could potentially be used as future improvements to the proposed system.

Visual object detection is a critical task for a variety of industrial applications, such as robot navigation, quality control and product assembling. Modern industrial environments require AI-based object detection methods that can achieve high accuracy, robustness and generalization. To this end, we propose a novel object detection approach that can process and fuse information from RGB-D images for the accurate detection of industrial objects. The proposed approach utilizes a novel Variational Faster R-CNN algorithm that aims to improve the robustness and generalization ability of the original Faster R-CNN algorithm by employing a VAE encoder-decoder network and a very powerful attention layer. Experimental results on two object detection datasets, namely the well-known RGB-D Washington dataset and the QCONPASS dataset of industrial objects that is first presented in this paper, verify the significant performance improvement achieved when the proposed approach is employed.

Object localization and detection is the emerging area of computer vision and image processing that finds out the location of the object in the video frames or in the digital images. Object localization and detection have many challenges like occlusion, scale variations, intraclass similarities, illumination conditions, pose variations, etc. Multi-view object detection focuses on different views of objects like the top, bottom, side view, etc. We aim to discuss the different Object detection models based on Machine learning and Deep neural network approaches in a multi-view environment. We also discuss different datasets used for object detections and their applications. We apply some object detection models like SSD and Faster R-CNN to specific object categories of Open Image Dataset V6 and compare the results based on mAP (Mean Average Precision).KeywordsObject detectionConvolution neural networksR-CNNFast R-CNNFaster R-CNNEfficientDetCenterNet

Falls are one of the major leading causes of mortality for elderly people living alone at home, which can lead to severe injuries. Fall detection is the most important health care issue for the elderly. In computer vision domain, significant breakthrough technologies such as deep learning have been obtained for over five years. Deep learning belongs to computational methods that allow an algorithm to program itself by learning from training data. Convolutional neural networks (CNNs), a specific type of deep learning, have set the state-of-the-art image classification performance in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) in recent years. In this paper, we present the use of convolutional neural networks for fall detection in video surveillance environment. CNN is directly applied to each frame image in the video to learn human shape deformation features that describe different postures of the human and determine if a fall occurs. Experimental results show that our proposed approach runs in real-time and achieves average accuracy of 99.98% for 10-fold cross-validation for fall detection. It is shown that the implemented CNN-based fall detection approach can be a promising solution for detecting falls.

Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this work, we aim to improve the cross-domain robustness of object detection. We tackle the domain shift on two levels: (1) the image-level shift, such as image style, illumination, etc., and (2) the instance-level shift, such as object appearance, size, etc. We build our approach based on the recent state-of-the-art Faster R-CNN model, and design two domain adaptation components, on image level and instance level, to reduce the domain discrepancy. The two domain adaptation components are based on <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">H</i> -divergence theory, and are implemented by learning a domain classifier in adversarial training manner. The domain classifiers on different levels are further reinforced with a consistency regularization to learn a domain-invariant region proposal network (RPN) in the Faster R-CNN model. We evaluate our newly proposed approach using multiple datasets including Cityscapes, KITTI, SIM10K, etc. The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.

In this paper, we will study the basic flow and the principle of state-of-the-art object detection technique (i.e. Faster R-CNN) and improve it further with the inclusion of two strategies into it. Firstly, we propose a multi-layer features merging strategy by using a concatenation layer. Secondly, we introduce a contextual learning scheme for Faster R-CNN. Previously, Faster R-CNN just uses regional features. Contextual features are added with the regional features for the classification and detection task. Our improvement on Faster R-CNN shows promising results. We call our improved Faster R-CNN network as ID-CNN (Intelligent Detection Using Convolutional Neural Network) as its detection accuracy is better. Therefore, we call it as an intelligent detector. We use a deep VGG-16 model as our base model, as Faster R-CNN did. We evaluated our ID-CNN on Pascal VOC public datasets. Experimental results show that ID-CNN can effectively improve the object detection average precision to some extent. On VOC 2007 and 2012, we achieved a mean average precision (mAP) of 74.7% and 71.9%, respectively. ID-CNN is also end-to-end trainable with the same alternating fine-tuning optimization scheme of Faster R-CNN. Finally, we compared ID-CNN with Faster R-CNN on ImageNet object detection dataset and we achieved mAP of 48.1% compared with 46.2% for Faster R-CNN.

Fast and accurate acquisition of the outline of rural buildings on remote sensing images is an efficient method to monitor illegal rural buildings. The traditional object detection method produces useless background information when detecting rural buildings; the semantic segmentation method cannot accurately segment the contours between buildings; the instance segmentation method cannot obtain regular building contours. The rotated object detection methods can effectively solve the problem that the traditional artificial intelligence method cannot accurately extract the outline of buildings. However, the rotated object detection methods are easy to lose location information of small objects in advanced feature maps and are sensitive to noise. To resolve these problems, this paper proposes a two-stage rotated object detection network for rural buildings (TRDet) by using a deep feature fusion network (DFF-Net) and a pixel attention module (PAM). Specifically, TRDet first fuses low-level location and high-level semantic information through the DFF-Net and then reduces the interference of noise information to the network through the PAM. The experimental results show that the mean average precession (mAP), precision, recall rate, and F1 score of the proposed TRDet are 83.57%, 91.11%, 86.5%, and 88.74%, respectively, which outperform the R2CNN model by 15%, 15.54%, 4.01%, and 9.87%. The results demonstrate that the TRDet can achieve better detection in small rural buildings and dense rural buildings.

The focus of the planned study is on finding lost people in crowded environments including public events, festivals, temples, and meetings. In today's busy environments, single-person identification is a challenging endeavor. This problem is addressed by applying a deep learning idea to arrive at a workable solution. Individuals are recognized through the use of a Convolutional Neural Network (CNN). Several face characteristics are used to positively identify the missing person. The use of Face Detection is crucial to the success of this endeavor. The ImageNet Large-Scale Visual Recognition Challenge participant AlexNet is used. The main takeaway is that the model's depth is crucial to its excellent performance, which is computationally expensive but is made possible by the use of graphics processing units (GPUs) during training. With sufficient training using a wide variety of images, it is possible to locate the sought-after object in the allotted space. The project's momentum is based on watching the live feed. Faces are extracted from the video and saved to a database. A collection of photos is available for use in making identifications. We use our own dataset to train the AlexNet's many layers. The images in the database are labelled according to whether or not they contain a person by utilizing the pretrained network. Additionally, the KLT method should be used to determine the person's location and enable real-time tracking.