Contextual Object Detection With Spatial Context Prototypes

Convolutional neural networks (CNNs) have been applied to learn spatial features for high-resolution (HR) synthetic aperture radar (SAR) image classification. However, there has been little work on integrating the unique statistical distributions of SAR images which can reveal physical properties of terrain objects, into CNNs in a supervised feature learning framework. To address this problem, a novel end-to-end supervised classification method is proposed for HR SAR images by considering both spatial context and statistical features. First, to extract more effective spatial features from SAR images, a new deep spatial context encoder network (DSCEN) is proposed, which is a lightweight structure and can be effectively trained with a small number of samples. Meanwhile, to enhance the diversity of statistics, the nonstationary joint statistical model (NS-JSM) is adopted to form the global statistical features. Specifically, SAR images are transformed into the Gabor wavelet domain and the produced multi-subbands magnitudes and phases are modeled by the log-normal and uniform distribution. The covariance matrix is further utilized to capture the inter-scale and intra-scale nonstationary correlation between the statistical subbands and make the joint statistical features more compact and distinguishable. Considering complementary advantages, a feature fusion network (Fusion-Net) base on group compression and smooth normalization is constructed to embed the statistical features into the spatial features and optimize the fusion feature representation. As a result, our model can learn the discriminative features and improve the final classification performance. Experiments on four HR SAR images validate the superiority of the proposed method over other related algorithms.

Generally, most approaches using methods such as cropping, rotating, and flipping achieve more data to train models for improving the accuracy of detection and segmentation. However, due to the difficulties of labeling such data especially semantic segmentation data, those traditional data augmentation methodologies cannot help a lot when the training set is really limited. In this paper, a model named OFA-Net (One For All Network) is proposed to combine object detection and semantic segmentation tasks. Meanwhile, using a strategy called “1-N Alternation” to train the OFA-Net model, which can make a fusion of features from detection and segmentation data. The results show that object detection data can be recruited to better the segmentation accuracy performance, and furthermore, segmentation data assist a lot to enhance the confidence of predictions for object detection. Finally, the OFA-Net model is trained without traditional data augmentation methodologies and tested on the KITTI test server. The model works well on the KITTI Road Segmentation challenge and can do a good job on the object detection task.

Hyperspectral Image (HSI) classification plays a key role remote sensing field. Recently, deep learning has demonstrated its effectiveness in HSI Classification field. This paper presents a spectral-spatial HSI classification technique established on the deep learning based deep belief network (DBN) for deep and abstract feature extraction and adaptive boundary adjustment based segmentation. Proposed approach focuses on integrating the deep learning based spectral features and segmentation based spatial features into a framework for improved performance. Specifically, first the deep DBN model is exploited as a spectral feature extraction based classifier to extract the deep spectral features. Second, spatial contextual features are obtained by utilizing effective adaptive boundary adjustment based segmentation technique. Finally, maximum voting based criteria is operated to integrate the results of extracted spectral and spatial information for improved HSI classification. In general, exploiting spectral features from DBN process and spatial features from segmentation and integration of spectral and spatial information by maximum voting based criteria, has a substantial effect on the performance of HSI classification. Experimental performance on real and widely used hyperspectral data sets with different contexts and resolutions demonstrates the accuracy of the proposed technique and performance is comparable to several recently proposed HSI classification techniques.

Computer vision (CV) and human-computer interaction (HCI) are essential in many technological fields. Researchers in CV are particularly interested in real-time object detection techniques, which have a wide range of applications, including inspection systems. In this study, we design and implement real-time object detection and recognition systems using the single-shoot detector (SSD) algorithm and deep learning techniques with pre-trained models. The system can detect static and moving objects in real-time and recognize the object's class. The primary goals of this research were to investigate and develop a real-time object detection system that employs deep learning and neural systems for real-time object detection and recognition. In addition, we evaluated the free available, pre-trained models with the SSD algorithm on various types of datasets to determine which models have high accuracy and speed when detecting an object. Moreover, the system is required to be operational on reasonable equipment. We tried and evaluated several deep learning structures and techniques during the coding procedure and developed and proposed a highly accurate and efficient object detection system. This system utilizes freely available datasets such as MS Common Objects in Context (COCO), PASCAL VOC, and Kitti. We evaluated our system's accuracy using various metrics such as precision and recall. The proposed system achieved a high accuracy of 97% while detecting and recognizing real-time objects.

Object detection, which is one of the most fundamental visual recognition tasks, has been a hotspot in computer vision. CNN (Convolutional Neural Networks) have been widely employed for building detector. Due to the success of RPN (Region Proposal Network), the two-stage detectors get both classification accuracy and precise regression bounding boxes. However, they still struggle in small-size object detection. In this paper, we present a deep network, namely Spatial Fine-Grained Network (SFGN). The SFGN that exploits Spatial Fine-Grained Features (SFGF) concatenates the higher resolution features, which is fine-grained with the low resolution features and high-level semantic by stacking spatial features for fine-grained features. An enhanced region proposal generator is proposed to get the objectless for small object to obtain a small set of proposal. The contextual information surrounding the region of interest is embedded using local spatial information for increasing the useful information and discriminating the background. For improving the detection performance, we use a simple yet surprisingly effective online hard example mining (OHEM) algorithm for training region proposal generator. It embeds an efficiently implemented soft non-maximum suppression (soft-NMS) for replacing with tradition NMS to obtain consistent improvements without increasing the computational complexity in inference. On PASCAL VOC 2007 and PASCAL VOC 2012 datasets, our SFGN improves baseline model from 81.2% mAP to 80.6% mAP. On MS COCO dataset, SFGN also performs better than baseline model. As intuition suggests, our detection results provide strong evidence that our SFGN improves detection accuracy, especially in small object test.

Multispectral systems for detection of concealed dangerous objects are becoming more popular because of their higher effectiveness compared to mono-spectral systems. So far, the problem of detecting objects hidden under clothing was considered only in the case of airports but it is becoming more important for public places like metro stations, and government buildings. Exploration of new spectral bands as well as development of technology result in introduction of new solutions – both mono and multispectral. It has been proved that objects hidden under clothing can be detected and visualized using terahertz (THz) cameras. However, passive THz cameras still offer too low image resolution for objects recognition. Limited range is another issue of passive imagers. On the other hand new infrared cameras offer sufficient parameters to detect objects covered with fabrics in some conditions, as well as high image quality and big pixel resolutions. The purpose of the studies is to investigate and compare the possibilities of using passive cameras operating in long wavelength infrared (LWIR) and THz spectral ranges for detection of concealed objects. For the purpose of investigations, commercial imagers operating in 6.5-11.7 μm and 250GHz (1.25mm) were used. In the article, we present the measurement setup and the results of measurements in various operating conditions. Theoretical studies of both spectral bands focused on detection of objects with passive imagers are also presented.

In recent years, Convolutional Neural Networks (CNNs) have repeatedly shown state-of-the-art performance for their accuracy in the task of object detection, but their heavy computational costs impede their ability for real-time detection when the supporting system is moving, particulary when it is accelerating. At the same time, recent progress on visual inertial systems takes great advantage of movement information to robustly estimate the robot state and its surrounding. This paper proposes to exploit the advantages of inertial odometry research for the purpose of real-time object detection system on mobile robots. We combine a CNN detector with VINS-Mono, a moving visual odometry system, and show reliable improvement in the detection process, especially when the robot accelerates or decelerates. Our system is ready-to-use in that it has very low deployment cost and requires no calibration. The resulting system allows for simultaneous robot state estimation and object detection, as well as object tracking. Lastly, this architecture proves to be flexible because not restrained to a specific object type or detector.

As the core technologies represented by Internet of Things (IoT) technology and computer vision technology booming, object detection algorithms based on deep learning have received high attention in various fields. Object detection is not only a core problem in the field of computer vision, but also a prerequisite and basis for many computer vision tasks, and has important applications in the fields of autonomous driving and video surveillance. The task of object detection is to find all the targets of interest in an image and determine their category and location. Object detection includes two tasks: object classification and object localization. However, object classification focuses on the most discriminative part of the feature map, and object localization requires a feature map focusing on the whole region of the object. Therefore, in order to improve the detection accuracy, we propose a CBAM-RetinaNet network model.CBAM (Convolutional Block Attention Module) is a lightweight convolutional attention module, which combines channel and spatial attention mechanism modules. The channel attention module focuses on the meaningful information in the input image, which would lead to an increase in the accuracy of object classification. The spatial attention module focuses on the location information of the object, which may improve the accuracy of object localization. The experiment results show that the proposed achieves better object detection performance on the PASCAL VOC2007 dataset, and the accuracy is 2% higher than that of the RetinaNet model, which has good experimental results.

Hyperspectral imagery contains both spatial structure information and abundant spectral features of imaged objects. However, due to sensor limitations, abundant spectral information always comes at the sacrifice of low spatial resolution, which brings about difficulties with object analysis and identification. The super-resolution (SR) of HSIs, restored by the traditional interpolation algorithms or the network models trained with the mean-square-error-based loss function, tends to produce over-smoothed images. In this paper, we propose a novel Hyperspectral imagery Spatial Super-Resolution algorithm based on a Generative Adversarial Network (HSSRGAN). The generator network in HSSRGAN consists of two interacting part, i.e., a spatial feature enhanced network (SFEN) and a spectral refined network (SRN), while the discriminator network is employed to predict the probability that the authentic HR image is comparatively more similar than the forged generated image. Concretely, SFEN with the special dense residual blocks is designed to fully extract and enhance more deep hierarchical spatial features of hyperspectral imagery, while SRN is constructed to capture spectral interrelationships and refine the spatial context informations so as to increase spatial resolution and alleviate spectral distortion. Moreover, SFEN and SRN are trained by the least-absolute-deviation based loss function to investigate spatial context and the spectral-angle-mapper based loss function to refine spectral information. We validate two versions of our proposed algorithm, 3D-HSSRGAN and 2D-HSSRGAN, on Pavia Centre dataset and Cuprite dataset. Experimental results show that the presented approach is superior to several existing state-of-the-art works.

Basic tasks in computer vision, object detection and localization have many applications in autonomous driving, robotics, surveillance, and healthcare [1]. Deep learning has enabled previously unheard-of levels of accuracy and robustness in object detection and localization tasks, revolutionizing the area in recent years. This paper provides a thorough overview of the most recent developments and approaches in the application of deep learning algorithms for localization and object detection. First, we go over the basic ideas behind object identification and localization, emphasizing the difficulties caused by different item sizes, occlusions, and cluttered backgrounds. We then explore the nuances of deep learning architectures designed specifically for these kinds of tasks: anchor-free approaches like Center Net, single-shot detectors like YOLO, and region-based detectors like Faster R-CNN. We investigate feature extraction networks, object detecting heads, and training procedures for best performance as we investigate the underlying mechanics of these architectures. We also go over important assessment measures and datasets that are necessary for benchmarking and training object detection algorithms. We stress the significance of using strong evaluation techniques to guarantee the dependability and capacity for generalization of the suggested algorithms. Apart from technical concerns, we investigate practical uses cases where object detection and localization are essential, like autonomous vehicle pedestrian identification, surveillance system object tracking, and medical imaging anomaly detection. Lastly, we examine new developments and directions for the discipline, such as integrating multimodal data, handling domain shifts, and improving object detection algorithms' interpretability and fairness. Our goal is to stimulate further developments in computer vision systems by offering scholars, professionals, and hobbyists insightful knowledge about the problems and cutting-edge methods of object recognition and localization through this thorough review. The content of the paper is succinctly summarized in this abstract, which also highlights the significance of deep learning, object detection and localization, important methodology, datasets, applications, and future developments in the field.

In this paper, we argue that there is a strong correlation between local 3D structure and object placement in everyday scenes. We call this the 3D context of the object. In previous work, this is typically hand-coded and limited to flat horizontal surfaces. In contrast, we propose to use a more general model for 3D context and learn the relationship between 3D context and different object classes. This way, we can capture more complex 3D contexts without implementing specialized routines. We present extensive experiments with both qualitative and quantitative evaluations of our method for different object classes. We show that our method can be used in conjunction with an object detection algorithm to reduce the rate of false positives. Our results support that the 3D structure surrounding objects in everyday scenes is a strong indicator of their placement and that it can give significant improvements in the performance of, for example, an object detection system. For evaluation, we have collected a large dataset of Microsoft Kinect frames from five different locations, which we also make publicly available.

Deep convolutional neural network (DCNN) based computer vision methods have great progress in object detection tasks. And object detection is essential to many applications such as autonomous robots and vehicles. However, it is difficult for object detection system to be deployed on embedded platforms due to its intensive computing architecture. We present an object detector MobileNet-SSD which can be deployed on embedded platforms. The object detector presented in this work based on Single Shot Detector (SSD) framework and replace the feature extractor with a more light weight network MobileNetV1. General matrix to matrix multiplication is used to simplify the calculation of convolution operation and is further optimized using ARM NEON technology. Finally, the object detector MobileNet-SSD is deployed on embedded platform and achieves 1.13FPS with 0.72 mean average precision on PASCAL VOC dataset.

Object detection is a major branch and fundamental task in computer vision, aiming to localize, identify and classify even the smallest objects of interest in images. Features can be extracted efficiently by deep convolutional neural networks (CNNs) as the backbone for real-time or near real-time object detection performance than the hand-crafted-based traditional methods. In the past few years, the advent of transformer-based models with robust self-attention mechanisms has not only raised object detection performance to a higher level but has also enabled it to produce excellent results. Many object detection tasks in the real world require that 3D information about the object be obtained, thus strengthening active research in 3D object detection. However, the algorithms for detecting 3D objects are not easy to propagate in real-world applications due to many factors, making reconstruction of 2D object detection algorithms to 3D object detection algorithms the suitable alternative. Therefore, we review the evolution of 2D object detection algorithms for digital imaging applications, focusing on their developments, models, applications, datasets, evaluation metrics, strengths and weaknesses, for better understanding of their landmarks and contributions to the advancement of the field.

Vegetation cover classification using mixed or low-resolution scalar images is challenging. Fortunately, recently deep learning object detection methods have emerged as a replacement to the conventional machine learning methods for the detection and classification of land use and land cover. This paper presents a deep learning object detection approach for land use and land cover detection using low/mixed resolution satellite images acquired from Google Earth satellite images. Google Earth images are accessible freely using the Google Earth Pro desktop application. Our dataset consists of two (02) classes (vegetation and non-vegetation) with a total of 450 labeled images captured from different parts of Pakistan. We present a comparison of the recent anchor-free object detection model YOLOX with the anchor-based object detection model YOLOR for solving real-time problems. The end-to-end differentiability, efficient GPU utilization, and absence of hand-crafted parameters make anchor-free models a compelling choice in object detection, and yet not been explored on Land cover classification using satellite images. Our experimental study shows that YOLOX delivers an overall accuracy of 83.50% on Vegetation and 86% on Non-Vegetation classes, which outperformed YOLOR by 30% on Vegetation classes and 34% on non-Vegetation classes for our dataset. We also show how an object detection system can be used for Vegetation and Non-Vegetation classification tasks, which can then be used for change monitoring and assisting in developing geographical maps using low/mixed resolution freely available satellite images.

Spatial context is a defining feature of episodic memories, which are often characterized as being events occurring in specific spatiotemporal contexts. In this review, I summarize research suggesting a common neural basis for episodic and spatial memory and relate this to the role of spatial context in episodic memory. I review evidence that spatial context serves as a scaffold for episodic memory and imagination, in terms of both behavioral and neural effects demonstrating a dependence of episodic memory on spatial representations. These effects are mediated by a posterior-medial set of neocortical regions, including the parahippocampal cortex, retrosplenial cortex, posterior cingulate cortex, precuneus, and angular gyrus, which interact with the hippocampus to represent spatial context in remembered and imagined events. I highlight questions and areas that require further research, including differentiation of hippocampal function along its long axis and subfields, and how these areas interact with the posterior-medial network. This article is categorized under: Psychology > Memory Neuroscience > Cognition.