Matching sonar images with high accuracy has been a problem for a long time, as sonar images are inherently hard to model due to reflections, noise and viewpoint dependence. Autonomous Underwater Vehicles require good sonar image matching capabilities for tasks such as tracking, simultaneous localization and mapping (SLAM) and some cases of object detection/recognition. We propose the use of Convolutional Neural Networks (CNN) to learn a matching function that can be trained from labeled sonar data, after pre-processing to generate matching and non-matching pairs. In a dataset of 39K training pairs, we obtain 0.91 Area under the ROC Curve (AUC) for a CNN that outputs a binary classification matching decision, and 0.89 AUC for another CNN that outputs a matching score. In comparison, classical keypoint matching methods like SIFT, SURF, ORB and AKAZE obtain AUC 0.61 to 0.68. Alternative learning methods obtain similar results, with a Random Forest Classifier obtaining AUC 0.79, and a Support Vector Machine resulting in AUC 0.66.
Hochschule Bonn-Rhein-Sieg（波恩-莱茵-锡格应用技术大学）；German Research Center for Artificial Intelligence（德国人工智能研究中心）
Application of underwater robots are on the rise, most of them are dependent on sonar for underwater vision, but the lack of strong perception capabilities limits them in this task. An important issue in sonar perception is matching image patches, which can enable other techniques like localization, change detection, and mapping. There is a rich literature for this problem in color images, but for acoustic images, it is lacking, due to the physics that produce these images. In this paper we improve on our previous results for this problem (Valdenegro-Toro et al, 2017), instead of modeling feat…
University of Groningen（格罗宁根大学）；Bonn-Rhein-Sieg University of Applied Sciences（波恩-莱茵-锡格应用科学大学）；Worcester Polytechnic Institute（伍斯特理工学院）；Heriot-Watt University（赫瑞瓦特大学）；German Research Center for Artificial Intelligence（德国人工智能研究中心）
ROSAR: An Adversarial Re-Training Framework for Robust Side-Scan Sonar Object Detection
RWTH Aachen University（亚琛工业大学）；INESC INOV-Lab（INESC创新实验室）；ISRC (ISEP/P.PORTO)（波尔图高等工程学院/波尔图大学的科学与研究中心）；INESC TEC（INESC技术与科学创新研究所）；Faculdade de Engenharia, Universidade do Porto（波尔图大学工程学院）
German Research Center for Artificial Intelligence（德国人工智能研究中心）
Detecting novel objects without class information is not trivial, as it is difficult to generalize from a small training set. This is an interesting problem for underwater robotics, as modeling marine objects is inherently more difficult in sonar images, and training data might not be available apriori. Detection proposals algorithms can be used for this purpose but usually requires a large amount of output bounding boxes. In this paper we propose the use of a fully convolutional neural network that regresses an objectness value directly from a Forward-Looking sonar image. By ranking objectnes…
This paper proposes a method that combines the style transfer technique and the learned descriptor to enhance the matching performances of underwater sonar images. In the field of underwater vision, sonar is currently the most effective long-distance detection sensor, it has excellent performances in map building and target search tasks. However, the traditional image matching algorithms are all developed based on optical images. In order to solve this contradiction, the style transfer method is used to convert the sonar images into optical styles, and at the same time, the learned descriptor …
In the field of deep-sea exploration, sonar is presently the only efficient long-distance sensing device. The complicated underwater environment, such as noise interference, low target intensity or background dynamics, has brought many negative effects on sonar imaging. Among them, the problem of nonlinear intensity is extremely prevalent. It is also known as the anisotropy of acoustic sensor imaging, that is, when autonomous underwater vehicles (AUVs) carry sonar to detect the same target from different angles, the intensity variation between image pairs is sometimes very large, which makes t…
School of Ocean Engineering, Harbin Institute of Technology（哈尔滨工业大学（威海）海洋工程学院）；School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学（威海）计算机科学与技术学院）
With the continuous development of underwater vision technology, more and more remote sensing images could be obtained. In the underwater scene, sonar sensors are currently the most effective remote perception devices, and the sonar images captured by them could provide rich environment information. In order to analyze a certain scene, we often need to merge the sonar images from different periods, various sonar frequencies and distinctive viewpoints. However, the above scenes will bring nonlinear intensity differences to the sonar images, which will make traditional matching methods almost in…
Object recognition is a fundamental problem in many video processing tasks, accurately locating seen objects at low computation cost paves the way for on-device video recognition. We propose PatchNet, an efficient convolutional neural network to match objects in adjacent video frames. It learns the patchwise correlation features instead of pixel features. PatchNet is very compact, running at just 58MFLOPs, $5\times$ simpler than MobileNetV2. We demonstrate its application on two tasks, video object detection and visual object tracking. On ImageNet VID, PatchNet reduces the flops of R-FCN ResNe…
In this work we propose a neural network based image descriptor suitable for image patch matching, which is an important task in many computer vision applications. Our approach is influenced by recent success of deep convolutional neural networks (CNNs) in object detection and classification tasks. We develop a model which maps the raw input patch to a low dimensional feature vector so that the distance between representations is small for similar patches and large otherwise. As a distance metric we utilize L2 norm, i.e. Euclidean distance, which is fast to evaluate and used in most popular ha…
Beyond Pixel Similarity: Task-Aware Evaluation of GAN-Based Synthetic Sonar Data for Robotic Perception
XITASO GmbH IT & Software Solutions（XITASO信息技术与软件解决方案有限公司）；National University of Sciences and Technology (NUST)（国立科技大学）；Technical University of Kaiserslautern（凯泽斯劳滕工业大学）
In this paper, we tackle the problem of one-shot unsupervised domain adaptation (OSUDA) for semantic segmentation where the segmentors only see one unlabeled target image during training. In this case, traditional unsupervised domain adaptation models usually fail since they cannot adapt to the target domain with over-fitting to one (or few) target samples. To address this problem, existing OSUDA methods usually integrate a style-transfer module to perform domain randomization based on the unlabeled target sample, with which multiple domains around the target sample can be explored during trai…
This thesis surveys the research in patch-based synthesis and algorithms for finding correspondences between small local regions of images. We additionally explore a large kind of applications of this new fast randomized matching technique. One of the algorithms we have studied in particular is PatchMatch, can find similar regions or "patches" of an image one to two orders of magnitude faster than previous techniques. The algorithmic program is driven by applying mathematical properties of nearest neighbors in natural images. It is observed that neighboring correspondences tend to be similar o…
University of Missouri（密苏里大学）；University of Florida（佛罗里达大学）；Naval Surface Warfare Center（海军水面战中心）
Topic models (e.g., pLSA, LDA, sLDA) have been widely used for segmenting imagery. However, these models are confined to crisp segmentation, forcing a visual word (i.e., an image patch) to belong to one and only one topic. Yet, there are many images in which some regions cannot be assigned a crisp categorical label (e.g., transition regions between a foggy sky and the ground or between sand and water at a beach). In these cases, a visual word is best represented with partial memberships across multiple topics. To address this, we present a partial membership latent Dirichlet allocation (PM-LDA…
Image patch matching, which is the process of identifying corresponding patches across images, has been used as a subroutine for many computer vision and image processing tasks. State -of-the-art patch matching techniques take image patches as input to a convolutional neural network to extract the patch features and evaluate their similarity. Our aim in this paper is to improve on the state of the art patch matching techniques by observing the fact that a sparse-overcomplete representation of an image posses statistical properties of natural visual scenes which can be exploited for patch match…
Garbage and waste disposal is one of the biggest challenges currently faced by mankind. Proper waste disposal and recycling is a must in any sustainable community, and in many coastal areas there is significant water pollution in the form of floating or submerged garbage. This is called marine debris. Submerged marine debris threatens marine life, and for shallow coastal areas, it can also threaten fishing vessels [Iñiguez et al. 2016, Renewable and Sustainable Energy Reviews]. Submerged marine debris typically stays in the environment for a long time (20+ years), and consists of materials tha…
Inner Mongolia University（内蒙古大学）；University of Hong Kong（香港大学）
Non-local self-similarity based low rank algorithms are the state-of-the-art methods for image denoising. In this paper, a new method is proposed by solving two issues: how to improve similar patches matching accuracy and build an appropriate low rank matrix approximation model for Gaussian noise. For the first issue, similar patches can be found locally or globally. Local patch matching is to find similar patches in a large neighborhood which can alleviate noise effect, but the number of patches may be insufficient. Global patch matching is to determine enough similar patches but the error ra…
Computational Biomedicine Lab（计算生物医学实验室）；University of Houston（休斯顿大学）
This paper focuses on improving face recognition performance by a patch-based 1-to-N signature matcher that learns correlations between different facial patches. A Fully Associative Patch-based Signature Matcher (FAPSM) is proposed so that the local matching identity of each patch contributes to the global matching identities of all the patches. The proposed matcher consists of three steps. First, based on the signature, the local matching identity and the corresponding matching score of each patch are computed. Then, a fully associative weight matrix is learned to obtain the global matching i…
Normandie Univ（诺曼底大学）；UNICAEN（卡昂大学）；ENSICAEN（卡昂国立高等工程师学院）；CNRS -- UMR GREYC（法国国家科学研究中心——GREYC联合研究单位）
Multimodal patch matching addresses the problem of finding the correspondences between image patches from two different modalities, e.g. RGB vs sketch or RGB vs near-infrared. The comparison of patches of different modalities can be done by discovering the information common to both modalities (Siamese like approaches) or the modality-specific information (Pseudo-Siamese like approaches). We observed that none of these two scenarios is optimal. This motivates us to propose a three-stream architecture, dubbed as TS-Net, combining the benefits of the two. In addition, we show that adding extra c…
This paper proposes a hierarchical multi-label matcher for patch-based face recognition. In signature generation, a face image is iteratively divided into multi-level patches. Two different types of patch divisions and signatures are introduced for 2D facial image and texture-lifted image, respectively. The matcher training consists of three steps. First, local classifiers are built to learn the local matching of each patch. Second, the hierarchical relationships defined between local patches are used to learn the global matching of each patch. Three ways are introduced to learn the global mat…
The non-local self-similarity property of natural images has been exploited extensively for solving various image processing problems. When it comes to video sequences, harnessing this force is even more beneficial due to the temporal redundancy. In the context of image and video denoising, many classically-oriented algorithms employ self-similarity, splitting the data into overlapping patches, gathering groups of similar ones and processing these together somehow. With the emergence of convolutional neural networks (CNN), the patch-based framework has been abandoned. Most CNN denoisers operat…
Many traditional computer vision algorithms generate realistic images by requiring that each patch in the generated image be similar to a patch in a training image and vice versa. Recently, this classical approach has been replaced by adversarial training with a patch discriminator. The adversarial approach avoids the computational burden of finding nearest neighbors of patches but often requires very long training times and may fail to match the distribution of patches. In this paper we leverage the recently developed Sliced Wasserstein Distance and develop an algorithm that explicitly and ef…
PATS: Patch Area Transportation with Subdivision for Local Feature Matching
State Key Lab of CAD&CG, Zhejiang University（浙江大学CAD&CG国家重点实验室）；ZJU-SenseTime Joint Lab of 3D Vision（浙江大学-商汤科技三维视觉联合实验室）；Multimedia Laboratory, The Chinese University of Hong Kong（香港中文大学多媒体实验室）
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；HUAWEI Technologies Co., Ltd.（华为技术有限公司）；Peng Cheng Laboratory（鹏城实验室）；Shenzhen University（深圳大学）
Beyond achieving higher compression efficiency over classical image compression codecs, deep image compression is expected to be improved with additional side information, e.g., another image from a different perspective of the same scene. To better utilize the side information under the distributed compression scenario, the existing method (Ayzik and Avidan 2020) only implements patch matching at the image domain to solve the parallax problem caused by the difference in viewing points. However, the patch matching at the image domain is not robust to the variance of scale, shape, and illuminat…
Visual Place Recognition (VPR) in areas with similar scenes such as urban or indoor scenarios is a major challenge. Existing VPR methods using global descriptors have difficulty capturing local specific regions (LSR) in the scene and are therefore prone to localization confusion in such scenarios. As a result, finding the LSR that are critical for location recognition becomes key. To address this challenge, we introduced Patch-NetVLAD+, which was inspired by patch-based VPR researches. Our method proposed a fine-tuning strategy with triplet loss to make NetVLAD suitable for extracting patch-le…
University of Twente（特文特大学）；Technical University of Brunswick（布伦瑞克工业大学）
Airborne laser scanning and photogrammetry are two main techniques to obtain 3D data representing the object surface. Due to the high cost of laser scanning, we want to explore the potential of using point clouds derived by dense image matching (DIM), as effective alternatives to laser scanning data. We present a framework to evaluate point clouds from dense image matching and derived Digital Surface Models (DSM) based on automatically extracted sample patches. Dense matching error and noise level are evaluated quantitatively at both the local level and whole block level. Experiments show that…
Template matching is one of the simplest methods used for eyes and mouth detection. However, it can be modified and extended to become a powerful tool. Since the patch itself plays a significant role in optimizing detection performance, a study on the influence of patch size and shape is carried out. The optimum patch size and shape is determined using the proposed method. Usually, template matching is also combined with other methods in order to improve detection accuracy. Thus, in this paper, the effectiveness of two image processing methods i.e. grayscale and Haar wavelet transform, when us…
Indian Institute of Technology Bombay（印度理工学院孟买分校）；Mercedes Benz Research and Development India（梅赛德斯-奔驰印度研发中心）
We propose a new dataset for learning local image descriptors which can be used for significantly improved patch matching. Our proposed dataset consists of an order of magnitude more number of scenes, images, and positive and negative correspondences compared to the currently available Multi-View Stereo (MVS) dataset from Brown et al. The new dataset also has better coverage of the overall viewpoint, scale, and lighting changes in comparison to the MVS dataset. Our dataset also provides supplementary information like RGB patches with scale and rotations values, and intrinsic and extrinsic came…
Indian Institute of Technology Bombay（印度理工学院孟买分校）；New York University（纽约大学）；Mercedes-Benz Research and Development India Pvt. Ltd.（梅赛德斯-奔驰印度研发私人有限公司）
We propose a convolutional neural network (ConvNet) based approach for learning local image descriptors which can be used for significantly improved patch matching and 3D reconstructions. A multi-resolution ConvNet is used for learning keypoint descriptors. We also propose a new dataset consisting of an order of magnitude more number of scenes, images, and positive and negative correspondences compared to the currently available Multi-View Stereo (MVS) [18] dataset. The new dataset also has better coverage of the overall viewpoint, scale, and lighting changes in comparison to the MVS dataset. …
Università degli Studi di Brescia（布雷西亚大学）；Politecnico di Torino（都灵理工大学）；Telecom Italia S.P.A.（意大利电信股份公司）
This work addresses the problem of learning compact yet discriminative patch descriptors within a deep learning framework. We observe that features extracted by convolutional layers in the pixel domain are largely complementary to features extracted in a transformed domain. We propose a convolutional network framework for learning binary patch descriptors where pixel domain features are fused with features extracted from the transformed domain. In our framework, while convolutional and transformed features are distinctly extracted, they are fused and provided to a single classifier which thus …
Human eyes can recognize person identities based on small salient regions, i.e. human saliency is distinctive and reliable in pedestrian matching across disjoint camera views. However, such valuable information is often hidden when computing similarities of pedestrian images with existing approaches. Inspired by our user study result of human perception on human saliency, we propose a novel perspective for person re-identification based on learning human saliency and matching saliency distribution. The proposed saliency learning and matching framework consists of four steps: (1) To handle misa…
School of Information Science and Engineering, Shandong University（山东大学信息科学与工程学院）；College of Geomatics, Shandong University of Science and Technology（山东科技大学测绘学院）；Shenzhen Research Institute, Shandong University（山东大学深圳研究院）；School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）
In deep learning-based local stereo matching methods, larger image patches usually bring better stereo matching accuracy. However, it is unrealistic to increase the size of the image patch size without restriction. Arbitrarily extending the patch size will change the local stereo matching method into the global stereo matching method, and the matching accuracy will be saturated. We simplified the existing Siamese convolutional network by reducing the number of network parameters and propose an efficient CNN based structure, namely Adaptive Deconvolution-based disparity matching Net (ADSM net) …
2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds
National University of Defense Technology（国防科技大学）；Defense Innovation Institute, Academy of Military Sciences（军事科学院国防科技创新研究院）；Sun Yat-sen University（中山大学）
University of Michigan（密歇根大学）；Imperial College London（帝国理工学院）
In stereoscope-based Minimally Invasive Surgeries (MIS), dense stereo matching plays an indispensable role in 3D shape recovery, AR, VR, and navigation tasks. Although numerous Deep Neural Network (DNN) approaches are proposed, the conventional prior-free approaches are still popular in the industry because of the lack of open-source annotated data set and the limitation of the task-specific pre-trained DNNs. Among the prior-free stereo matching algorithms, there is no successful real-time algorithm in none GPU environment for MIS. This paper proposes the first CPU-level real-time prior-free s…
Shandong University（山东大学）；Shandong Jianzhu University（山东建筑大学）；the Second Hospital of Shandong University（山东大学第二医院）
Digital image inpainting is an interpolation problem, inferring the content in the missing (unknown) region to agree with the known region data such that the interpolated result fulfills some prior knowledge. Low-rank and nonlocal self-similarity are two important priors for image inpainting. Based on the nonlocal self-similarity assumption, an image is divided into overlapped square target patches (submatrices) and the similar patches of any target patch are reshaped as vectors and stacked into a patch matrix. Such a patch matrix usually enjoys a property of low rank or approximately low rank…
Relational Representation Learning Network for Cross-Spectral Image Patch Matching
Chinese Academy of Sciences（中国科学院）；Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences（中国科学院机器人与智能制造创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Xidian University（西安电子科技大学）；The Chinese University of Hong Kong（香港中文大学）
Faculty of Computer and Information Science（计算机与信息科学学院）；University of Ljubljana（卢布尔雅那大学）；Courant Institute of Mathematical Sciences（库朗数学科学研究所）；New York University（纽约大学）；Facebook AI Research（脸书人工智能研究院）
We present a method for extracting depth information from a rectified image pair. Our approach focuses on the first stage of many stereo algorithms: the matching cost computation. We approach the problem by learning a similarity measure on small image patches using a convolutional neural network. Training is carried out in a supervised manner by constructing a binary classification data set with examples of similar and dissimilar pairs of patches. We examine two network architectures for this task: one tuned for speed, the other for accuracy. The output of the convolutional neural network is u…
This paper presents a generic pre-processor for expediting conventional template matching techniques. Instead of locating the best matched patch in the reference image to a query template via exhaustive search, the proposed algorithm rules out regions with no possible matches with minimum computational efforts. While working on simple patch features, such as mean, variance and gradient, the fast pre-screening is highly discriminative. Its computational efficiency is gained by using a novel octagonal-star-shaped template and the inclusion-exclusion principle to extract and compare patch feature…
Chongqing Key Laboratory of Emergency Communication（重庆应急通信重点实验室）；Chongqing Communication Institute（重庆通信学院）
Initializing optical flow field by either sparse descriptor matching or dense patch matches has been proved to be particularly useful for capturing large displacements. In this paper, we present a pyramidal gradient matching approach that can provide dense matches for highly accurate and efficient optical flow estimation. A novel contribution of our method is that image gradient is used to describe image patches and proved to be able to produce robust matching. Therefore, our method is more efficient than methods that adopt special features (like SIFT) or patch distance metric. Moreover, we fi…
