Explore the vast range of titles available.

This paper addresses real-time moving object detection with high accuracy in high-resolution video frames. A previously developed framework for moving object detection is modified to enable real-time processing of high-resolution images. First, a computationally efficient method is employed, which detects moving regions on a resized image while maintaining moving regions on the original image with mapping coordinates. Second, a light backbone deep neural network in place of a more complex one is utilized. Third, the focal loss function is employed to alleviate the imbalance between positive and negative samples. The results of the extensive experimentations conducted indicate that the modified framework developed in this paper achieves a processing rate of 21 frames per second with 86.15% accuracy on the dataset SimitMovingDataset, which contains high-resolution images of the size 1920 × 1080.

Detection and localization of regions of images that attract immediate human visual attention is currently an intensive area of research in computer vision. The capability of automatic identification and segmentation of such salient image regions has immediate consequences for applications in the field of computer vision, computer graphics, and multimedia. A large number of salient object detection (SOD) methods have been devised to effectively mimic the capability of the human visual system to detect the salient regions in images. These methods can be broadly categorized into two categories based on their feature engineering mechanism: conventional or deep learning-based. In this survey, most of the influential advances in image-based SOD from both conventional as well as deep learning-based categories have been reviewed in detail. Relevant saliency modeling trends with key issues, core techniques, and the scope for future research work have been discussed in the context of difficulties often faced in salient object detection. Results are presented for various challenging cases for some large-scale public datasets. Different metrics considered for assessment of the performance of state-of-the-art salient object detection models are also covered. Some future directions for SOD are presented towards end.

Although there are well established object detection methods based on static images, their application to video data on a frame by frame basis faces two shortcomings: (i) lack of computational efficiency due to redundancy across image frames or by not using a temporal and spatial correlation of features across image frames, and (ii) lack of robustness to real-world conditions such as motion blur and occlusion. Since the introduction of the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) in 2015, a growing number of methods have appeared in the literature on video object detection, many of which have utilized deep learning models. The aim of this paper is to provide a review of these papers on video object detection. An overview of the existing datasets for video object detection together with commonly used evaluation metrics is first presented. Video object detection methods are then categorized and a description of each of them is stated. Two comparison tables are provided to see their differences in terms of both accuracy and computational efficiency. Finally, some future trends in video object detection to address the challenges involved are noted.

In unmanned aerial vehicle photographs, object detection algorithms encounter challenges in enhancing both speed and accuracy for objects of different sizes, primarily due to complex backgrounds and small objects. This study introduces the PDWT-YOLO algorithm, based on the YOLOv7-tiny model, to improve the effectiveness of object detection across all sizes. The proposed method enhances the detection of small objects by incorporating a dedicated small-object detection layer, while reducing the conflict between classification and regression tasks through the replacement of the YOLOv7-tiny model’s detection head (IDetect) with a decoupled head. Moreover, network convergence is accelerated, and regression accuracy is improved by replacing the Complete Intersection over Union (CIoU) loss function with a Wise Intersection over Union (WIoU) focusing mechanism in the loss function. To assess the proposed model’s effectiveness, it was trained and tested on the VisDrone-2019 dataset comprising images captured by various drones across diverse scenarios, weather conditions, and lighting conditions. The experiments show that mAP@0.5:0.95 and mAP@0.5 increased by 5% and 6.7%, respectively, with acceptable running speed compared with the original YOLOv7-tiny model. Furthermore, this method shows improvement over other datasets, confirming that PDWT-YOLO is effective for multiscale object detection.

The object detection algorithm is mainly focused on detection in general scenarios, when the same algorithm is applied to drone-captured scenes, and the detection performance of the algorithm will be significantly reduced. Our research found that small objects are the main reason for this phenomenon. In order to verify this finding, we choose the yolov5 model and propose four methods to improve the detection precision of small object based on it. At the same time, considering that the model needs to be small in size, speed fast, low cost and easy to deploy in actual application, therefore, when designing these four methods, we also fully consider the impact of these methods on the detection speed. The model integrating all the improved methods not only greatly improves the detection precision, but also effectively reduces the loss of detection speed. Finally, based on VisDrone-2020, the mAP of our model is increased from 12.7 to 37.66%, and the detection speed is up to 55FPS. It is to outperform the earlier state of the art in detection speed and promote the progress of object detection algorithms on drone platforms.

Daily acquisition of large amounts of aerial and satellite images has facilitated subsequent automatic interpretations of these images. One such interpretation is object detection. Despite the great progress made in this domain, the detection of multi-scale objects, especially small objects in high resolution satellite (HRS) images, has not been adequately explored. As a result, the detection performance turns out to be poor. To address this problem, we first propose a unified multi-scale convolutional neural network (CNN) for geospatial object detection in HRS images. It consists of a multi-scale object proposal network and a multi-scale object detection network, both of which share a multi-scale base network. The base network can produce feature maps with different receptive fields to be responsible for objects with different scales. Then, we use the multi-scale object proposal network to generate high quality object proposals from the feature maps. Finally, we use these object proposals with the multi-scale object detection network to train a good object detector. Comprehensive evaluations on a publicly available remote sensing object detection dataset and comparisons with several state-of-the-art approaches demonstrate the effectiveness of the presented method. The proposed method achieves the best mean average precision (mAP) value of 89.6%, runs at 10 frames per second (FPS) on a GTX 1080Ti GPU.

Underwater marine object detection, as one of the most fundamental techniques in the community of marine science and engineering, has been shown to exhibit tremendous potential for exploring the oceans in recent years. It has been widely applied in practical applications, such as monitoring of underwater ecosystems, exploration of natural resources, management of commercial fisheries, etc. However, due to complexity of the underwater environment, characteristics of marine objects, and limitations imposed by exploration equipment, detection performance in terms of speed, accuracy, and robustness can be dramatically degraded when conventional approaches are used. Deep learning has been found to have significant impact on a variety of applications, including marine engineering. In this context, we offer a review of deep learning-based underwater marine object detection techniques. Underwater object detection can be performed by different sensors, such as acoustic sonar or optical cameras. In this paper, we focus on vision-based object detection due to several significant advantages. To facilitate a thorough understanding of this subject, we organize research challenges of vision-based underwater object detection into four categories: image quality degradation, small object detection, poor generalization, and real-time detection. We review recent advances in underwater marine object detection and highlight advantages and disadvantages of existing solutions for each challenge. In addition, we provide a detailed critical examination of the most extensively used datasets. In addition, we present comparative studies with previous reviews, notably those approaches that leverage artificial intelligence, as well as future trends related to this hot topic.

With the goal to detect both the object categories appearing in the training phase and those never have been observed before testing, zero-shot object detection (ZSD) becomes a challenging yet anticipated task in the community. Current approaches tackle this problem by drawing on the feature synthesis techniques used in the zero-shot image classification (ZSC) task without delving into the inherent problems of ZSD. In this paper, we analyze the out-standing challenges that ZSD presents compared with ZSC—severe intra-class variation, complex category co-occurrence, open test scenario, and reveal their interference to the region feature synthesis process. In view of this, we propose a novel memory-based robust region feature synthesizer (M-RRFS) for ZSD, which is equipped with the Intra-class Semantic Diverging (IntraSD), the Inter-class Structure Preserving (InterSP), and the Cross-Domain Contrast Enhancing (CrossCE) mechanisms to overcome the inadequate intra-class diversity, insufficient inter-class separability, and weak inter-domain contrast problems. Moreover, when designing the whole learning framework, we develop an asynchronous memory container (AMC) to explore the cross-domain relationship between the seen class domain and unseen class domain to reduce the overlap between the distributions of them. Based on AMC, a memory-assisted ZSD inference process is also proposed to further boost the prediction accuracy. To evaluate the proposed approach, comprehensive experiments on MS-COCO, PASCAL VOC, ILSVRC and DIOR datasets are conducted, and superior performances have been achieved. Notably, we achieve new state-of-the-art performances on MS-COCO dataset, i.e., 64.0%, 60.9% and 55.5% Recall@100 with IoU =0.4,0.5,0.6 respectively, and 15.1% mAp with IoU=0.5, under the 48/17 category split setting. Meanwhile, experiments on the DIOR dataset actually build the earliest benchmark for evaluating zero-shot object detection performance on remote sensing images. https://github.com/HPL123/M-RRFS.

Metal surface defect detection has been a challenge in the industrial field. The current metal surface defect algorithms target only at a few types of defects and fail to perform well on defects with different scales. In this paper, a large number of metal surface defects are studied based on GC10-DET data set. An improved yolov5 detection network is designed targeting defects of various scales, especially of small-scaled objects, using a specific data enhancement method to regularize and an effective loss function to address data imbalance caused by small-scaled object defects. Finally, the comparative experiment on GC10-DET data set proves the major improvements on accuracy superiority of the proposed method.

The inherent ambiguity in ground-truth annotations of 3D bounding boxes, caused by occlusions, signal missing, or manual annotation errors, can confuse deep 3D object detectors during training, thus deteriorating detection accuracy. However, existing methods overlook such issues to some extent and treat the labels ass deterministic. In this paper, we formulate the label uncertainty problem as the diversity of potentially plausible bounding boxes of objects. Then, we propose GLENet, a generative framework adapted from conditional variational autoencoders, to model the one-to-many relationship between a typical 3D object and its potential ground-truth bounding boxes with latent variables. The label uncertainty generated by GLENet is a plug-and-play module and can be conveniently integrated into existing deep 3D detectors to build probabilistic detectors and supervise the learning of the localization uncertainty. Besides, we propose an uncertainty-aware quality estimator architecture in probabilistic detectors to guide the training of the IoU-branch with predicted localization uncertainty. We incorporate the proposed methods into various popular base 3D detectors and demonstrate significant and consistent performance gains on both KITTI and Waymo benchmark datasets. Especially, the proposed GLENet-VR outperforms all published LiDAR-based approaches by a large margin and achieves the top rank among single-modal methods on the challenging KITTI test set. The source code and pre-trained models are publicly available at https://github.com/Eaphan/GLENet.