Search

View-based methods have demonstrated promising performance in 3D shape understanding. However, they tend to make strong assumptions about the relations between views or learn the multi-view correlations indirectly, which limits the flexibility of exploring inter-view correlations and the effectiveness of target tasks. To overcome the above problems, this paper investigates flexible organization and explicit correlation learning for multiple views. In particular, we propose to incorporate different views of a 3D shape into a permutation-invariant set, referred to as \emph{View Set}, which removes rigid relation assumptions and facilitates adequate information exchange and fusion among views. Based on that, we devise a nimble Transformer model, named \emph{VSFormer}, to explicitly capture pairwise and higher-order correlations of all elements in the set. Meanwhile, we theoretically reveal a natural correspondence between the Cartesian product of a view set and the correlation matrix in the attention mechanism, which supports our model design. Comprehensive experiments suggest that VSFormer has better flexibility, efficient inference efficiency and superior performance. Notably, VSFormer reaches state-of-the-art results on various 3d recognition datasets, including ModelNet40, ScanObjectNN and RGBD. It also establishes new records on the SHREC'17 retrieval benchmark. The code and datasets are available at \url{https://github.com/auniquesun/VSFormer}., Comment: accepted by TVCG 2024

Detecting locally, non-overlapping, near-clique densest subgraphs is a crucial problem for community search in social networks. As a vertex may be involved in multiple overlapped local cliques, detecting locally densest sub-structures considering h-clique density, i.e., locally h-clique densest subgraph (LhCDS) attracts great interests. This paper investigates the LhCDS detection problem and proposes an efficient and exact algorithm to list the top-k non-overlapping, locally h-clique dense, and compact subgraphs. We in particular jointly consider h-clique compact number and LhCDS and design a new "Iterative Propose-Prune-and-Verify" pipeline (IPPV) for top-k LhCDS detection. (1) In the proposal part, we derive initial bounds for h-clique compact numbers; prove the validity, and extend a convex programming method to tighten the bounds for proposing LhCDS candidates without missing any. (2) Then a tentative graph decomposition method is proposed to solve the challenging case where a clique spans multiple subgraphs in graph decomposition. (3) To deal with the verification difficulty, both a basic and a fast verification method are proposed, where the fast method constructs a smaller-scale flow network to improve efficiency while preserving the verification correctness. The verified LhCDSes are returned, while the candidates that remained unsure reenter the IPPV pipeline. (4) We further extend the proposed methods to locally more general pattern densest subgraph detection problems. We prove the exactness and low complexity of the proposed algorithm. Extensive experiments on real datasets show the effectiveness and high efficiency of IPPV., Comment: This paper has been accepted by SIGMOD 2025

For interacting with mobile objects in unfamiliar environments, simultaneously locating, mapping, and tracking the 3D poses of multiple objects are crucially required. This paper proposes a Tracklet Graph and Query Graph-based framework, i.e., GSLAMOT, to address this challenge. GSLAMOT utilizes camera and LiDAR multimodal information as inputs and divides the representation of the dynamic scene into a semantic map for representing the static environment, a trajectory of the ego-agent, and an online maintained Tracklet Graph (TG) for tracking and predicting the 3D poses of the detected mobile objects. A Query Graph (QG) is constructed in each frame by object detection to query and update TG. For accurate object association, a Multi-criteria Star Graph Association (MSGA) method is proposed to find matched objects between the detections in QG and the predicted tracklets in TG. Then, an Object-centric Graph Optimization (OGO) method is proposed to simultaneously optimize the TG, the semantic map, and the agent trajectory. It triangulates the detected objects into the map to enrich the map's semantic information. We address the efficiency issues to handle the three tightly coupled tasks in parallel. Experiments are conducted on KITTI, Waymo, and an emulated Traffic Congestion dataset that highlights challenging scenarios. Experiments show that GSLAMOT enables accurate crowded object tracking while conducting SLAM accurately in challenging scenarios, demonstrating more excellent performances than the state-of-the-art methods. The code and dataset are at https://gslamot.github.io., Comment: 11 pages, 9 figures, ACM MM 2024

Image matching aims at identifying corresponding points between a pair of images. Currently, detector-free methods have shown impressive performance in challenging scenarios, thanks to their capability of generating dense matches and global receptive field. However, performing feature interaction and proposing matches across the entire image is unnecessary, because not all image regions contribute to the matching process. Interacting and matching in unmatchable areas can introduce errors, reducing matching accuracy and efficiency. Meanwhile, the scale discrepancy issue still troubles existing methods. To address above issues, we propose PRogressive dependency maxImization for Scale-invariant image Matching (PRISM), which jointly prunes irrelevant patch features and tackles the scale discrepancy. To do this, we firstly present a Multi-scale Pruning Module (MPM) to adaptively prune irrelevant features by maximizing the dependency between the two feature sets. Moreover, we design the Scale-Aware Dynamic Pruning Attention (SADPA) to aggregate information from different scales via a hierarchical design. Our method's superior matching performance and generalization capability are confirmed by leading accuracy across various evaluation benchmarks and downstream tasks. The code is publicly available at https://github.com/Master-cai/PRISM., Comment: 15 pages, 8 figures, ACM MM 2024. Supplementary materials are included

Collaborative autonomous driving with multiple vehicles usually requires the data fusion from multiple modalities. To ensure effective fusion, the data from each individual modality shall maintain a reasonably high quality. However, in collaborative perception, the quality of object detection based on a modality is highly sensitive to the relative pose errors among the agents. It leads to feature misalignment and significantly reduces collaborative performance. To address this issue, we propose RoCo, a novel unsupervised framework to conduct iterative object matching and agent pose adjustment. To the best of our knowledge, our work is the first to model the pose correction problem in collaborative perception as an object matching task, which reliably associates common objects detected by different agents. On top of this, we propose a graph optimization process to adjust the agent poses by minimizing the alignment errors of the associated objects, and the object matching is re-done based on the adjusted agent poses. This process is carried out iteratively until convergence. Experimental study on both simulated and real-world datasets demonstrates that the proposed framework RoCo consistently outperforms existing relevant methods in terms of the collaborative object detection performance, and exhibits highly desired robustness when the pose information of agents is with high-level noise. Ablation studies are also provided to show the impact of its key parameters and components. The code is released at https://github.com/HuangZhe885/RoCo., Comment: ACM MM2024

Multi-object tracking (MOT) on static platforms, such as by surveillance cameras, has achieved significant progress, with various paradigms providing attractive performances. However, the effectiveness of traditional MOT methods is significantly reduced when it comes to dynamic platforms like drones. This decrease is attributed to the distinctive challenges in the MOT-on-drone scenario: (1) objects are generally small in the image plane, blurred, and frequently occluded, making them challenging to detect and recognize; (2) drones move and see objects from different angles, causing the unreliability of the predicted positions and feature embeddings of the objects. This paper proposes DroneMOT, which firstly proposes a Dual-domain Integrated Attention (DIA) module that considers the fast movements of drones to enhance the drone-based object detection and feature embedding for small-sized, blurred, and occluded objects. Then, an innovative Motion-Driven Association (MDA) scheme is introduced, considering the concurrent movements of both the drone and the objects. Within MDA, an Adaptive Feature Synchronization (AFS) technique is presented to update the object features seen from different angles. Additionally, a Dual Motion-based Prediction (DMP) method is employed to forecast the object positions. Finally, both the refined feature embeddings and the predicted positions are integrated to enhance the object association. Comprehensive evaluations on VisDrone2019-MOT and UAVDT datasets show that DroneMOT provides substantial performance improvements over the state-of-the-art in the domain of MOT on drones., Comment: 8 pages, 6 figures, ICRA 2024

The availability of city-scale Lidar maps enables the potential of city-scale place recognition using mobile cameras. However, the city-scale Lidar maps generally need to be compressed for storage efficiency, which increases the difficulty of direct visual place recognition in compressed Lidar maps. This paper proposes VOLoc, an accurate and efficient visual place recognition method that exploits geometric similarity to directly query the compressed Lidar map via the real-time captured image sequence. In the offline phase, VOLoc compresses the Lidar maps using a \emph{Geometry-Preserving Compressor} (GPC), in which the compression is reversible, a crucial requirement for the downstream 6DoF pose estimation. In the online phase, VOLoc proposes an online Geometric Recovery Module (GRM), which is composed of online Visual Odometry (VO) and a point cloud optimization module, such that the local scene structure around the camera is online recovered to build the \emph{Querying Point Cloud} (QPC). Then the QPC is compressed by the same GPC, and is aggregated into a global descriptor by an attention-based aggregation module, to query the compressed Lidar map in the vector space. A transfer learning mechanism is also proposed to improve the accuracy and the generality of the aggregation network. Extensive evaluations show that VOLoc provides localization accuracy even better than the Lidar-to-Lidar place recognition, setting up a new record for utilizing the compressed Lidar map by low-end mobile cameras. The code are publicly available at https://github.com/Master-cai/VOLoc., Comment: 8 pages, 7figures, ICRA 2024

This paper presents a parameter-efficient prompt tuning method, named PPT, to adapt a large multi-modal model for 3D point cloud understanding. Existing strategies are quite expensive in computation and storage, and depend on time-consuming prompt engineering. We address the problems from three aspects. Firstly, a PromptLearner module is devised to replace hand-crafted prompts with learnable contexts to automate the prompt tuning process. Then, we lock the pre-trained backbone instead of adopting the full fine-tuning paradigm to substantially improve the parameter efficiency. Finally, a lightweight PointAdapter module is arranged near target tasks to enhance prompt tuning for 3D point cloud understanding. Comprehensive experiments are conducted to demonstrate the superior parameter and data efficiency of the proposed method.Meanwhile, we obtain new records on 4 public datasets and multiple 3D tasks, i.e., point cloud recognition, few-shot learning, and part segmentation. The implementation is available at https://github.com/auniquesun/PPT., Comment: 9 pages, 5 figures, 6 tables; accepted by ICRA 2024

In the realm of intelligent transportation systems, accurate and reliable traffic monitoring is crucial. Traditional devices, such as cameras and lidars, face limitations in adverse weather conditions and complex traffic scenarios, prompting the need for more resilient technologies. This paper presents traffic flow monitoring method using optical fiber-based Distributed Acoustic Sensors (DAS). An innovative vehicle trajectory extraction algorithm is proposed to derive traffic flow statistics. In the processing of optical fiber waterfall diagrams, Butterworth low-pass filter and peaks location search method are employed to determine the entry position of vehicles. Subsequently, line-by-line matching algorithm is proposed to effectively track the trajectories. Experiments were conducted under both real highway and tunnel scenarios, showing that our approach not only extracts vehicle trajectories more accurately than the classical Hough and Radon transform-based methods, but also facilitates the calculation of traffic flow information using the low-cost acoustic sensors. It provides a new reliable means for traffic flow monitoring which can be integrated with existing methods., Comment: 10 pages,23 figures, references added

This paper presents ViewFormer, a simple yet effective model for multi-view 3d shape recognition and retrieval. We systematically investigate the existing methods for aggregating multi-view information and propose a novel ``view set" perspective, which minimizes the relation assumption about the views and releases the representation flexibility. We devise an adaptive attention model to capture pairwise and higher-order correlations of the elements in the view set. The learned multi-view correlations are aggregated into an expressive view set descriptor for recognition and retrieval. Experiments show the proposed method unleashes surprising capabilities across different tasks and datasets. For instance, with only 2 attention blocks and 4.8M learnable parameters, ViewFormer reaches 98.8% recognition accuracy on ModelNet40 for the first time, exceeding previous best method by 1.1% . On the challenging RGBD dataset, our method achieves 98.4% recognition accuracy, which is a 4.1% absolute improvement over the strongest baseline. ViewFormer also sets new records in several evaluation dimensions of 3D shape retrieval defined on the SHREC'17 benchmark., Comment: 15 pages, 10 figures, 16 tables

One fundamental limitation to the research of bird strike prevention is the lack of a large-scale dataset taken directly from real-world airports. Existing relevant datasets are either small in size or not dedicated for this purpose. To advance the research and practical solutions for bird strike prevention, in this paper, we present a large-scale challenging dataset AirBirds that consists of 118,312 time-series images, where a total of 409,967 bounding boxes of flying birds are manually, carefully annotated. The average size of all annotated instances is smaller than 10 pixels in 1920x1080 images. Images in the dataset are captured over 4 seasons of a whole year by a network of cameras deployed at a real-world airport, covering diverse bird species, lighting conditions and 13 meteorological scenarios. To the best of our knowledge, it is the first large-scale image dataset that directly collects flying birds in real-world airports for bird strike prevention. This dataset is publicly available at https://airbirdsdata.github.io/., Comment: 17 pages, 9 figures, 3 tables; accepted by ACCV 2022

For robust visual-inertial SLAM in perceptually-challenging indoor environments,recent studies exploit line features to extract descriptive information about scene structure to deal with the degeneracy of point features. But existing point-line-based SLAM methods mainly use Pl\"ucker matrix or orthogonal representation to represent a line, which needs to calculate at least four variables to determine a line. Given the numerous line features to determine in each frame, the overly flexible line representation increases the computation burden and comprises the accuracy of the results. In this paper, we propose inverse depth representation for a line, which models each extracted line feature using only two variables, i.e., the inverse depths of the two ending points. It exploits the fact that the projected line's pixel coordinates on the image plane are rather accurate, which partially restrict the line. Using this compact line presentation, Inverse Depth Line SLAM (IDLS) is proposed to track the line features in SLAM in an accurate and efficient way. A robust line triangulation method and a novel line re-projection error model are introduced. And a two-step optimization method is proposed to firstly determine the lines and then to estimate the camera poses in each frame. IDLS is extensively evaluated in multiple perceptually-challenging datasets. The results show it is more accurate, robust, and needs lower computational overhead than the current state-of-the-art of point-line-based SLAM methods.

Recently, a growing number of work design unsupervised paradigms for point cloud processing to alleviate the limitation of expensive manual annotation and poor transferability of supervised methods. Among them, CrossPoint follows the contrastive learning framework and exploits image and point cloud data for unsupervised point cloud understanding. Although the promising performance is presented, the unbalanced architecture makes it unnecessarily complex and inefficient. For example, the image branch in CrossPoint is $\sim$8.3x heavier than the point cloud branch leading to higher complexity and latency. To address this problem, in this paper, we propose a lightweight Vision-and-Pointcloud Transformer (ViPFormer) to unify image and point cloud processing in a single architecture. ViPFormer learns in an unsupervised manner by optimizing intra-modal and cross-modal contrastive objectives. Then the pretrained model is transferred to various downstream tasks, including 3D shape classification and semantic segmentation. Experiments on different datasets show ViPFormer surpasses previous state-of-the-art unsupervised methods with higher accuracy, lower model complexity and runtime latency. Finally, the effectiveness of each component in ViPFormer is validated by extensive ablation studies. The implementation of the proposed method is available at https://github.com/auniquesun/ViPFormer., Comment: 9 pages, 4 figures, 7 tables; accepted by ICRA 2023

Indoor route graph learning is critically important for autonomous indoor navigation. A key problem for crowd-sourcing indoor route graph learning is featured trajectory generation. In this paper, a system is provided to generate featured trajectories by crowd-sourcing smartphone data. Firstly, we propose a more accurate PDR algorithm for the generation of trajectory motion data. This algorithm uses ADAPTIV as the step counting method and uses the step estimation algorithm o make the trajectory more accurate in length. Next, the barometer is used to segment the tracks of different floors, and the track floors are obtained by WiFi feature clustering. Finally, by finding the turning point as the feature point of the trajectory, the vertices and edges of the trajectory are extracted to reduce the noise of the long straight trajectory.

Distributed algorithms to solve linear equations in multi-agent networks have attracted great research attention and many iteration-based distributed algorithms have been developed. The convergence speed is a key factor to be considered for distributed algorithms, and it is shown dependent on the spectral radius of the iteration matrix. However, the iteration matrix is determined by the network structure and is hardly pre-tuned, making the iterative-based distributed algorithms may converge very slowly when the spectral radius is close to 1. In contrast, in centralized optimization, the Conjugate Gradient (CG) is a widely adopted idea to speed up the convergence of the centralized solvers, which can guarantee convergence in fixed steps. In this paper, we propose a general distributed implementation of CG, called DCG. DCG only needs local communication and local computation, while inheriting the characteristic of fast convergence. DCG guarantees to converge in $4Hn$ rounds, where $H$ is the maximum hop number of the network and $n$ is the number of nodes. We present the applications of DCG in solving the least square problem and network localization problem. The results show the convergence speed of DCG is three orders of magnitude faster than the widely used Richardson iteration method.

Determining whether nodes can be uniquely localized, called localizability detection, is a concomitant problem of network localization. Localizability under traditional Non-Linear Localization (NLL) schema has been well explored, whereas localizability under the emerging Barycentric coordinate-based Linear Localization (BLL) schema has not been well touched. In this paper, we investigate the deficiency of existing localizability theories and algorithms in BLL, and then propose a necessary condition and a sufficient condition for BLL node localizability. Based on these two conditions, an efficient iterative maximum flow (IMF) algorithm is designed to identify BLL localizable nodes. Finally, our algorithms are validated by both theoretical analysis and experimental evaluations.

Accurate and robust localization is crucial for wireless ad-hoc and sensor networks. Among the localization techniques, component-based methods advance themselves for conquering network sparseness and anchor sparseness. But component-based methods are sensitive to ranging noises, which may cause a huge accumulated error either in component realization or merging process. This paper presents three results for robust component-based localization under ranging noises. (1) For a rigid graph component, a novel method is proposed to evaluate the graph's possible number of flip ambiguities under noises. In particular, graph's \emph{MInimal sepaRators that are neaRly cOllineaR (MIRROR)} is presented as the cause of flip ambiguity, and the number of MIRRORs indicates the possible number of flip ambiguities under noise. (2) Then the sensitivity of a graph's local deforming regarding ranging noises is investigated by perturbation analysis. A novel Ranging Sensitivity Matrix (RSM) is proposed to estimate the node location perturbations due to ranging noises. (3) By evaluating component robustness via the flipping and the local deforming risks, a Robust Component Generation and Realization (RCGR) algorithm is developed, which generates components based on the robustness metrics. RCGR was evaluated by simulations, which showed much better noise resistance and locating accuracy improvements than state-of-the-art of component-based localization algorithms., Comment: 9 pages, 15 figures, ICCCN 2018, Hangzhou, China