Search

• A new path planning method based on obstacles for a grid map is proposed. • After optimization by convex hulls, the simple point set is generated. • The hierarchical obstacles are used to plan the path quickly in a small scope. • Multi-objective D* Lite algorithm is adopted to optimize the length and smoothness. • The path is smoothed by cubic Bezier curves to fit the real robot. In the past few decades, many results have been achieved in the research of mobile robot path planning, and they have been applied in simple scenarios, such as factory AGV, bank guide robot. However, path planning in highly dense and complex scenarios has become an important challenge for applications. Robots face dense map and complex obstacles and hardly find out an optimal path within a reasonable period, such as unmanned vehicles in freight ports and rescue robots in earthquake environment. Therefore, a multi-obstacle path planning and optimization method is proposed. In order to simplify complex environmental obstacles, the obstacles will be divided into basis obstacles and extension obstacles. Firstly, the basis obstacles and their contour point sets are determined according to the starting point and goal point. Furthermore, the basis obstacles are optimized by convex hulls, and then the corresponding basis point set is obtained. Secondly, the extension obstacles are determined by the basis point set, starting point and goal point, and then the corresponding extension point set is generated. After that, a path planner is designed by the multi-objective D* Lite algorithm for distance and smoothness in order to get reasonable and optimized path in a complex environment. Moreover, the path is smoothed by cubic bezier curves to fit the kinematic model of the robot. Finally, The proposed method conduct comparative experiments with other algorithms to verify its accuracy and computational efficiency of planning in complex environments. [ABSTRACT FROM AUTHOR]

Visual localization, a fundamental component of several computer vision tasks, has been predominantly realized by scene coordinate regression (SCoRe) techniques. These methods leverage neural networks for scene coordinates prediction, followed by a PnP algorithm to recover the 6-DOF camera pose. However, similar image patches are prevalent in indoor scenes, which results in the extraction of comparable features for the regression of different scene coordinates. As a result, the localization accuracy is severely declined. In this work, we develop ALNet, a novel SCoRe method that incorporates a local discrepancy perception module (LDPM) and an adaptive channel attention module (ACAM) to address this challenge. For LDPM, our key insight lies in that scene attributes around different similar image patches are inconsistent. Technically, for each image patch, LDPM identifies a certain number of the most dissimilar patches around it and computes difference vectors to enrich its own features, thereby enabling the differentiation of similar image patches. Considering geometric attributes are beneficial for distinguishing similar patches while semantic context is conducive to encoding regression issues, integrating multi-level features is an effective approach to elevate the localization accuracy. Therefore, ACAM concatenates multi-level features together and leverages both average pooling and max pooling to generate reliable channel-wise weighting coefficient, thereby modeling the correlation among channels to integrate multi-level features effectively. Comprehensive experiments are conducted on mainstream indoor localization benchmarks and an actual environment, showing that ALNet achieves impressive performance. Source code and the experimental results video are available at https://github.com/DAMMONGAO/alnet. • We propose a SCoRe-based method that achieves excellent localization accuracy. • We propose a module to distinguish similar image patches to improve accuracy. • We propose an attention module to integrate multi-level features. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel method for dynamic label assignment in temporal action detection (TAD) called Optimal Action Segment Assignment (OASA). The OASA method converts label assignment into an optimal transportation problem by computing the cost matrix between predicted temporal action segments and groundtruths. The unit transportation cost between a predicted temporal segment and a groundtruth pair is defined as the weighted summation of action classification loss and temporal localization loss. Additionally, we deploy Adaptive Estimation of Candidate Segment Number (AE-CSN) to adaptively determine the number of positive samples for each groundtruth. After formulation, the label assignment problem is converted to find a global optimal assignment plan by minimizing the cost. Therefore, OASA eliminates the need for manually designed prior parameters, which exist in fixed label assignment methods, and improves the generalization of the algorithm between different datasets. To evaluate OASA, we also introduce a simple anchor-free temporal action detector called ActionMixer. It consists of two components: Temporal Mixer and Channel Mixer. The Temporal Mixer employs depth-wise convolution layers with large kernels to capture temporal information, while the Channel Mixer mixes and extracts features across the channel dimension. Extensive experiments conducted on the THUMOS-14, ActivityNet-1.3, and EPIC-Kitchens-100 datasets show that ActionMixer equipped with OASA achieves state-of-the-art performance, surpassing other advanced temporal action detection methods. • Optimal Action Segment Assignment is proposed for Temporal Action Detection. • Optimal Action Segment Assignment removes the temporal prior. • ActionMixer is proposed to evaluate Optimal Action Segment Assignment. • ActionMixer achieves state-of-the-art performance on the popular benchmarks. [ABSTRACT FROM AUTHOR]

Local feature matching constitutes the cornerstone of multiple computer vision applications (e.g., 3D reconstruction and long-term visual localization), and has been successfully resolved by detector-free methods. To further improve the matching performance, more recent research has focused on designing sophisticated architectures but endures additional computational overhead. In this study, with a different perspective from previous studies, we aim to develop a deep and compact matching network to improve performance while reducing computing cost. The key insight is that a local feature matcher with deep layers can capture more human-intuitive and simpler-to-match features. To this end, we propose DeepMatcher, a deep transformer-based network that tackles the inherent obstacles of not being able to build a deep local feature matcher with current methods. DeepMatcher consists of: (1) a local feature extractor (LFE), (2) a feature-transition module (FTM), (3) a slimming transformer (SlimFormer), (4) a coarse matches module (CMM), and (5) a fine matches module (FMM). The LFE is utilized to generate dense keypoints with enriched features from the images. We then introduce the FTM to ensure a smooth transition of feature scopes from LFE to the subsequent SlimFormer because of their different receptive fields. Subsequently, we develop SlimFormer dedicated to DeepMatcher, which leverages vector-based attention to model the relevance among all keypoints, enabling the network to construct a deep Transformer architecture with less computational cost. Relative position encoding is applied to each SlimFormer to explicitly disclose the relative distance information, thereby improving the representation of the keypoints. A layer-scale strategy is also employed in each SlimFormer to enable the network to adaptively assimilate message exchange, thus endowing it to simulate human behavior, in which humans can acquire different matching cues each time they scan an image pair. By interleaving the self- and cross-SlimFormers multiple times, DeepMatcher can easily establish pixel-wise dense matches at the coarse level using the CMM. Finally, we consider match refinement as a combination of classification and regression problems and design an FMM to predict confidence and offset concurrently, thus generating robust and accurate matches. Compared with our baseline LoFTR in indoor/outdoor pose estimation, DeepMatcher surpasses it by 3.32%/2.91% in AUC@5 ∘. Besides, DeepMatcher and DeepMatcher-L significantly reduce computational cost and only consume 77.89% and 92.46% GFLOPs of LoFTR. Large DeepMatcher considerably outperforms state-of-the-art methods on several benchmarks, including outdoor pose estimation (MegaDepth dataset), indoor pose estimation (ScanNet dataset), homography estimation (HPatches dataset), and image matching (HPatches dataset), demonstrating the superior matching capability of a deep local feature matcher. • We propose DeepMatcher, a deep Transformer-based network for local feature matching. • We propose SlimFormer to enable DeepMatcher to be extended into dozen layers. • We propose FTM to ensure a smooth transition from CNN to SlimFormer. • We propose FMM to optimize coarse matches, deriving robust and accurate matches. [ABSTRACT FROM AUTHOR]

Local feature matching involves the task of establishing the pixel-wise correspondences between a pair of images. As an integral component of plentiful computer vision applications (e.g., visual localization), this task has been successfully performed using Transformer-based methods. However, these methods typically extract numerous keypoints from sparse texture regions to construct a densely-connected graph neural network (GNN) for long-range feature aggregation, which inevitably triggers redundant message exchange and hampers the learning process. Furthermore, they employ transformer encoder layers that consider images as 1D sequences, leaving them incapable of extracting multiscale local structural information from the images, which is critical for establishing correspondence in image pairs with significantly scales shifts. In this study, we develop FMAP, an innovative detector-free approach that enables accurate local feature matching. For the first issue, FMAP employs an anchor points feature aggregation module (APAM) that captures representative keypoints and discards the extraneous keypoints to build a sparsified GNN for compact yet clean message exchange, with the key insight that the keypoints containing abundant visual information are distinguishable from their neighbors. For the second issue, FMAP proposes a global–local multiscale perception module (GMPM), which incorporates abundant multiscale local context information into global feature representation by employing multiple depth-wise convolutions with varying kernel sizes, thereby generating discriminative features that are robust to scale shifts. In addition, the depth-wise convolutions are utilized in the feed-forward network of the GMPM to further fuse the global context information and local feature representation. Extensive experiments on several standard benchmarks demonstrate that the proposed FMAP method significantly outperforms state-of-the-art methods. Compared to the cutting-edge methods MatchFormer, QuadTree, and TopicFM in relative pose estimation task, FMAP surpasses them by 2.27%, 0.58%, and 1.08% in terms of AUC@5°. Besides, FMAP noticeably outperforms the baseline LoFTR by (2. 38 % , 1. 89 % , 1. 45 %) in terms of AUC@(5°, 10°, 20°). Moreover, we integrate FMAP into an official visual localization framework and conduct a visual localization experiment, with the results showing that FMAP exceeds LoFTR by 2.3% in terms of AP. • We propose a Transformer-based method that achieves excellent matching accuracy. • We constructs sparsified GNN to alleviate redundant message exchange. • We integrate global context and multi-scale local features to boost robustness. [ABSTRACT FROM AUTHOR]