LONG-TERM VISUAL LOCALIZATION IN LARGE SCALE URBAN ENVIRONMENTS EXPLOITING STREET LEVEL IMAGERY

Any city-scale visual localization system has to overcome long-term appearance changes, such as varying illumination conditions or seasonal changes between query and database images. Since semantic content is more robust to such changes, we exploit semantic information to improve visual localization. In our scenario, the database consists of gnomonic views generated from panoramic images (e.g. Google Street View) and query images are collected with a standard field-of-view camera at a different time. To improve localization, we check the semantic similarity between query and database images, which is not trivial since the position and viewpoint of the cameras do not exactly match. To learn similarity, we propose training a CNN in a self-supervised fashion with contrastive learning on a dataset of semantically segmented images. With experiments we showed that this semantic similarity estimation approach works better than measuring the similarity at pixel-level. Finally, we used the semantic similarity scores to verify the retrievals obtained by a state-of-the-art visual localization method and observed that contrastive learning-based pose verification increases top-1 recall value to 0.90 which corresponds to a 2% improvement.

In this paper, we present a novel coarse-to-fine visual localization approach: contextual visual localization. This approach relies on three elements: (i) a minimal-complexity classifier for performing fast coarse localization (submap classification); (ii) an optimized saliency detector which exploits the visual statistics of the submap; and (iii) a fast view-matching algorithm which filters initial matchings with a structural criterion. The latter algorithm yields fine localization. Our experiments show that these elements have been successfully integrated for solving the global localization problem. Context, that is, the awareness of being in a particular submap, is defined by a supervised classifier tuned for a minimal set of features. Visual context is exploited both for tuning (optimizing) the saliency detection process, and to select potential matching views in the visual database, close enough to the query view.

Motivated by the recent success of supervised and weakly supervised common object discovery, in this paper, we move forward one step further to tackle common object discovery in a fully unsupervised way. Generally, object co-localization aims at simultaneously localizing objects of the same class across a group of images. Traditional object localization/detection usually trains specific object detectors which require bounding box annotations of object instances, or at least image-level labels to indicate the presence/absence of objects in an image. Given a collection of images without any annotations, our proposed fully unsupervised method is to simultaneously discover images that contain common objects and also localize common objects in corresponding images. Without requiring to know the total number of common objects, we formulate this unsupervised object discovery as a sub-graph mining problem from a weighted graph of object proposals, where nodes correspond to object proposals, and edges represent the similarities between neighbouring proposals. The positive images and common objects are jointly discovered by finding sub-graphs of strongly connected nodes, with each sub-graph capturing one object pattern. The optimization problem can be efficiently solved by our proposed maximal-flow-based algorithm. Instead of assuming that each image contains only one common object, our proposed solution can better address wild images where each image may contain multiple common objects or even no common object. Moreover, our proposed method can be easily tailored to the task of image retrieval in which the nodes correspond to the similarity between query and reference images. Extensive experiments on PASCAL VOC 2007 and Object Discovery data sets demonstrate that even without any supervision, our approach can discover/localize common objects of various classes in the presence of scale, view point, appearance variation, and partial occlusions. We also conduct broad experiments on image retrieval benchmarks, Holidays and Oxford5k data sets, to show that our proposed method, which considers both the similarity between query and reference images and also similarities among reference images, can help to improve the retrieval results significantly.

Change detection, or anomaly detection, from street-view images acquired by an autonomous robot at multiple different times, is a major problem in robotic mapping and autonomous driving. Formulation as an image comparison task, which operates on a given pair of query and reference images is common to many existing approaches to this problem. Unfortunately, providing relevant reference images is not straightforward. In this paper, we propose a novel formulation for change detection, termed compressive change retrieval, which can operate on a query image and similar reference images retrieved from the web. Compared to previous formulations, there are two sources of difficulty. First, the retrieved reference images may frequently contain non-relevant reference images, because even state-of-the-art place-recognition techniques suffer from retrieval noise. Second, image comparison needs to be conducted in a compressed domain to minimize the storage cost of large collections of street-view images. To address the above issues, we also present a practical change detection algorithm that uses compressed bag-of-words (BoW) image representation as a scalable solution. The results of experiments conducted on a practical change detection task, "moving object detection (MOD)," using the publicly available Malaga dataset validate the effectiveness of the proposed approach.

One of the techniques in region based image retrieval (RBIR) is comparing the global feature of an entire image and the local feature of image’s sub-block in query and database image. The determined sub-block must be able to detect an object with varying sizes and locations. So the sub-block with flexible size and location is needed. We propose a new method for local feature extraction by determining the flexible size and location of sub-block based on the transition region in region based image retrieval. Global features of both query and database image are extracted using invariant moment. Local features in database and query image are extracted using hue, saturation, and value (HSV) histogram and local binary patterns (LBP). There are several steps to extract the local feature of sub-block in the query image. First, preprocessing is conducted to get the transition region, then the flexible sub-block is determined based on the transition region. Afterward, the local feature of sub-block is extracted. The result of this application is the retrieved images ordered by the most similar to the query image. The local feature extraction with the proposed method is effective for image retrieval with precision and recall value are 57%.

Visual localization has been well studied in recent decades and applied in many fields as a fundamental capability in robotics. However, the success of the state of the arts usually builds on the assumption that the environment is static. In dynamic scenarios where moving objects are present, the performance of the existing visual localization systems degrades a lot due to the disturbance of the dynamic factors. To address this problem, we propose a novel sparse motion removal (SMR) model that detects the dynamic and static regions for an input frame based on a Bayesian framework. The similarity between the consecutive frames and the difference between the current frame and the reference frame are both considered to reduce the detection uncertainty. After the detection process is finished, the dynamic regions are eliminated while the static ones are fed into a feature-based visual simultaneous localization and mapping (SLAM) system for further visual localization. To verify the proposed method, both qualitative and quantitative experiments are performed and the experimental results have demonstrated that the proposed model can significantly improve the accuracy and robustness for visual localization in dynamic environments.<;/p><;p><;i>Note to Practitioners<;/i>-This article was motivated by the visual localization problem in dynamic environments. Visual localization is well applied in many robotic fields such as path planning and exploration as the basic capability for a mobile robot. In the GPS-denied environments, one robot needs to localize itself through perceiving the unknown environment based on a visual sensor. In real-world scenes, the existence of the moving objects will significantly degrade the localization accuracy, which makes the robot implementation unreliable. In this article, an SMR model is designed to handle this problem. Once receiving a frame, the proposed model divides it into dynamic and static regions through a Bayesian framework. The dynamic regions are eliminated, while the static ones are maintained and fed into a feature-based visual SLAM system for further visual localization. The proposed method greatly improves the localization accuracy in dynamic environments and guarantees the robustness for robotic implementation.

Visual localization is an attractive problem that estimates the camera localization from database images based on the query image. It is a crucial task for various applications, such as autonomous vehicles, assistive navigation and augmented reality. The challenging issues of the task lie in various appearance variations between query and database images, including illumination variations, dynamic object variations and viewpoint variations. In order to tackle those challenges, Panoramic Annular Localizer into which panoramic annular lens and robust deep image descriptors are incorporated is proposed in this paper. The panoramic annular images captured by the single camera are processed and fed into the NetVLAD network to form the active deep descriptor, and sequential matching is utilized to generate the localization result. The experiments carried on the public datasets and in the field illustrate the validation of the proposed system.

Intelligent visual localization of wireless capsule endoscopes enhanced by color information

Place recognition and visual localization are particularly challenging in wide baseline configurations. In this letter, we contribute with the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Danish Airs and Grounds</i> (DAG) dataset, a large collection of street-level and aerial images targeting such cases. Its main challenge lies in the extreme viewing-angle difference between query and reference images with consequent changes in illumination and perspective. The dataset is larger and more diverse than current publicly available data, including more than 50 km of roads in urban, suburban and rural areas. All images are associated with accurate 6-DoF metadata that allows the benchmarking of visual localization methods. Additionally, we validate our data by presenting the results of a simple map-to-image re-localization baseline. that first estimates a dense 3D reconstruction from the aerial images and then matches query street-level images to street-level renderings of the 3D model. The dataset can be downloaded at:.

In feature-based visual localization for small-scale scenes, local descriptors are used to estimate the camera pose of a query image. For large and ambiguous environments, learning-based hierarchical networks that employ local as well as global descriptors to reduce the search space of database images into a smaller set of reference views have been introduced. However, since global descriptors are generated using visual features, reference images with some of these features may be erroneously selected. In order to address this limitation, this paper proposes two clustering methods based on how often features appear as well as their covisibility. For both approaches, the scene is represented by voxels whose size and number are computed according to the size of the scene and the number of available 3D points. In the first approach, a voxel-based histogram representing highly reoccurring scene regions is generated from reference images. A meanshift is then employed to group the most highly reoccurring voxels into place clusters based on their spatial proximity. In the second approach, a graph representing the covisibility-based relationship of voxels is built. Local matching is performed within the reference image clusters, and a perspective-n-point is employed to estimate the camera pose. The experimental results showed that camera pose estimation using the proposed approaches was more accurate than that of previous methods.

Due to the huge growth of the World Wide Web, medical images are now available in large numbers in online repositories, and there exists the need to retrieval the images through automatically extracting visual information of the medical images, which is commonly known as content-based image retrieval (CBIR). Since each feature extracted from images just characterizes certain aspect of image content, multiple features are necessarily employed to improve the retrieval performance. Meanwhile, experiments demonstrate that a special feature is not equally important for different image queries. Most of existed feature fusion methods for image retrieval only utilize query independent feature fusion or rely on explicit user weighting. In this paper, we present a novel query dependent feature fusion method for medical image retrieval based on one class support vector machine. Having considered that a special feature is not equally important for different image queries, the proposed query dependent feature fusion method can learn different feature fusion models for different image queries only based on multiply image samples provided by the user, and the learned feature fusion models can reflect the different importances of a special feature for different image queries. The experimental results on the IRMA medical image collection demonstrate that the proposed method can improve the retrieval performance effectively and can outperform existed feature fusion methods for image retrieval.

With the rapid advancement of digital imaging technologies, and the use of large volume image databases in various applications, it becomes imperative to build an automatic and an efficient image retrieval system. Content Based Image Retrieval (CBIR) is most emerging and vivid research area in computer vision, in which unknown query image assigns to the closest possible similar images available in the database. Current systems mainly use colour, texture, and shape information for image retrieval using similarity measures between query and database images features. Here this work, proposed a classification system that allows recognizing and recovering the class of a query image based on its visual content. This successful categorization of images greatly enhances the performance of retrieval by filtering out irrelevant classes. In this way we have done the comparative analysis of various features as an individual or in combinations, with direct similarity measure and proposed framework. Experimentson benchmark Wang database show that the proposed classification & retrieval framework performs significantly better than the common framework of distances.

A new indexing system for multiresolution image retrieval has been developed. The system analyzes not only whole images but also--for the first time--local features present in the images. This capability is important in managing large-scale image systems such as video databases and medical image databases. Key to the method is the use of an innovative wavelet, called the W-transform. This transform is characterized by its ability to handle signals of arbitrary size. Equally important, the W-transform is not constrained by assumptions about periodicity. That is, the transformed signal in some location is related only to the signals at its neighboring location. These properties make the W-transform a natural tool for analyzing local image features. A brief discussion is given of how the system works. The feature-oriented image indexing and retrieval method offers two major advantages over traditional multiresolution histogram comparison methods. The response time for retrieving image coarse components is considerably faster than that for retrieving whole images--thereby dramatically speeding image retrieval over the Ethernet. Moreover, the new method can be used to search images that are significantly different from the query image as a whole but contain local features identical with or similar to those in the query image.

Abstract. In this paper, we present a method for visual localization and pose estimation based on 3D image spaces. The method works in indoor and outdoor environments and does not require the presence of control points or markers. The method is evaluated with different sensors in an outdoor and an indoor test field. The results of our research show the viability of single image localization with absolute position accuracies at the decimetre level for outdoor environments and 5 cm or better for indoor environments. However, the evaluation also revealed a number of limitations of single image visual localization in real-world environments. Some of them could be addressed by an alternative AR-based localization approach, which we also present and compare in this paper. We then discuss the strengths and weaknesses of the two approaches and show possibilities for combining them to obtain accurate and robust visual localization in an absolute coordinate frame.

Image Indexing and Retrieval Using Object-based Point Feature Maps