arXiv subjects

Yiqun Li

Publications and source records attributed to Yiqun Li.

29 records · Page 2Linked to original sources

arXiv2024

Fast Safe Rectangular Corridor-based Online AGV Trajectory Optimization with Obstacle Avoidance

Automated Guided Vehicles (AGVs) are essential in various industries for their efficiency and adaptability. However, planning trajectories for AGVs in obstacle-dense, unstructured environments presents significant challenges due to the nonholonomic kinematics, abundant obstacles, and the scenario's nonconvex and constrained nature. To address this, we propose an efficient trajectory planning framework for AGVs by formulating the problem as an optimal control problem. Our framework utilizes the fast safe rectangular corridor (FSRC) algorithm to construct rectangular convex corridors, representing avoidance constraints as box constraints. This eliminates redundant obstacle influences and accelerates the solution speed. Additionally, we employ the Modified Visibility Graph algorithm to speed up path planning and a boundary discretization strategy to expedite FSRC construction. Experimental results demonstrate the effectiveness and superiority of our framework, particularly in computational efficiency. Compared to advanced frameworks, our framework achieves computational efficiency gains of 1 to 2 orders of magnitude. Notably, FSRC significantly outperforms other safe convex corridor-based methods regarding computational efficiency.

cs.RO↗

arXiv2024

Exploiting Low-level Representations for Ultra-Fast Road Segmentation

Achieving real-time and accuracy on embedded platforms has always been the pursuit of road segmentation methods. To this end, they have proposed many lightweight networks. However, they ignore the fact that roads are "stuff" (background or environmental elements) rather than "things" (specific identifiable objects), which inspires us to explore the feasibility of representing roads with low-level instead of high-level features. Surprisingly, we find that the primary stage of mainstream network models is sufficient to represent most pixels of the road for segmentation. Motivated by this, we propose a Low-level Feature Dominated Road Segmentation network (LFD-RoadSeg). Specifically, LFD-RoadSeg employs a bilateral structure. The spatial detail branch is firstly designed to extract low-level feature representation for the road by the first stage of ResNet-18. To suppress texture-less regions mistaken as the road in the low-level feature, the context semantic branch is then designed to extract the context feature in a fast manner. To this end, in the second branch, we asymmetrically downsample the input image and design an aggregation module to achieve comparable receptive fields to the third stage of ResNet-18 but with less time consumption. Finally, to segment the road from the low-level feature, a selective fusion module is proposed to calculate pixel-wise attention between the low-level representation and context feature, and suppress the non-road low-level response by this attention. On KITTI-Road, LFD-RoadSeg achieves a maximum F1-measure (MaxF) of 95.21% and an average precision of 93.71%, while reaching 238 FPS on a single TITAN Xp and 54 FPS on a Jetson TX2, all with a compact model size of just 936k parameters. The source code is available at https://github.com/zhouhuan-hust/LFD-RoadSeg.

cs.CV↗

arXiv2024

Local modification of subdiffusion by initial Fickian diffusion: Multiscale modeling, analysis and computation

We propose a local modification of the standard subdiffusion model by introducing the initial Fickian diffusion, which results in a multiscale diffusion model. The developed model resolves the incompatibility between the nonlocal operators in subdiffusion and the local initial conditions and thus eliminates the initial singularity of the solutions of the subdiffusion, while retaining its heavy tail behavior away from the initial time. The well-posedness of the model and high-order regularity estimates of its solutions are analyzed by resolvent estimates, based on which the numerical discretization and analysis are performed. Numerical experiments are carried out to substantiate the theoretical findings.

math.NA↗

arXiv2023

SCA-PVNet: Self-and-Cross Attention Based Aggregation of Point Cloud and Multi-View for 3D Object Retrieval

To address 3D object retrieval, substantial efforts have been made to generate highly discriminative descriptors of 3D objects represented by a single modality, e.g., voxels, point clouds or multi-view images. It is promising to leverage the complementary information from multi-modality representations of 3D objects to further improve retrieval performance. However, multi-modality 3D object retrieval is rarely developed and analyzed on large-scale datasets. In this paper, we propose self-and-cross attention based aggregation of point cloud and multi-view images (SCA-PVNet) for 3D object retrieval. With deep features extracted from point clouds and multi-view images, we design two types of feature aggregation modules, namely the In-Modality Aggregation Module (IMAM) and the Cross-Modality Aggregation Module (CMAM), for effective feature fusion. IMAM leverages a self-attention mechanism to aggregate multi-view features while CMAM exploits a cross-attention mechanism to interact point cloud features with multi-view features. The final descriptor of a 3D object for object retrieval can be obtained via concatenating the aggregated features from both modules. Extensive experiments and analysis are conducted on three datasets, ranging from small to large scale, to show the superiority of the proposed SCA-PVNet over the state-of-the-art methods.

cs.CV↗

arXiv2023

A time-fractional optimal transport and mean-field planning: Formulation and algorithm

The time-fractional optimal transport (OT) and mean-field planning (MFP) models are developed to describe the anomalous transport of the agents in a heterogeneous environment such that their densities are transported from the initial density distribution to the terminal one with the minimal cost. We derive a strongly coupled nonlinear system of a time-fractional transport equation and a backward time-fractional Hamilton-Jacobi equation based on the first-order optimality condition. The general-proximal primal-dual hybrid gradient (G-prox PDHG) algorithm is applied to discretize the OT and MFP formulations, in which a preconditioner induced by the numerical approximation to the time-fractional PDE is derived to accelerate the convergence of the algorithm for both problems. Numerical experiments for OT and MFP problems between Gaussian distributions and between image densities are carried out to investigate the performance of the OT and MFP formulations. Those numerical experiments also demonstrate the effectiveness and flexibility of our proposed algorithm.

math.OC↗

arXiv2021

Few-Shot Defect Segmentation Leveraging Abundant Normal Training Samples Through Normal Background Regularization and Crop-and-Paste Operation

In industrial product quality assessment, it is essential to determine whether a product is defect-free and further analyze the severity of anomality. To this end, accurate defect segmentation on images of products provides an important functionality. In industrial inspection tasks, it is common to capture abundant defect-free image samples but very limited anomalous ones. Therefore, it is critical to develop automatic and accurate defect segmentation systems using only a small number of annotated anomalous training images. This paper tackles the challenging few-shot defect segmentation task with sufficient normal (defect-free) training images but very few anomalous ones. We present two effective regularization techniques via incorporating abundant defect-free images into the training of a UNet-like encoder-decoder defect segmentation network. We first propose a Normal Background Regularization (NBR) loss which is jointly minimized with the segmentation loss, enhancing the encoder network to produce distinctive representations for normal regions. Secondly, we crop/paste defective regions to the randomly selected normal images for data augmentation and propose a weighted binary cross-entropy loss to enhance the training by emphasizing more realistic crop-and-pasted augmented images based on feature-level similarity comparison. Both techniques are implemented on an encoder-decoder segmentation network backboned by ResNet-34 for few-shot defect segmentation. Extensive experiments are conducted on the recently released MVTec Anomaly Detection dataset with high-resolution industrial images. Under both 1-shot and 5-shot defect segmentation settings, the proposed method significantly outperforms several benchmarking methods.

cs.CV↗

arXiv2020

UDC 2020 Challenge on Image Restoration of Under-Display Camera: Methods and Results

This paper is the report of the first Under-Display Camera (UDC) image restoration challenge in conjunction with the RLQ workshop at ECCV 2020. The challenge is based on a newly-collected database of Under-Display Camera. The challenge tracks correspond to two types of display: a 4k Transparent OLED (T-OLED) and a phone Pentile OLED (P-OLED). Along with about 150 teams registered the challenge, eight and nine teams submitted the results during the testing phase for each track. The results in the paper are state-of-the-art restoration performance of Under-Display Camera Restoration. Datasets and paper are available at https://yzhouas.github.io/projects/UDC/udc.html.

eess.IV↗

arXiv2020

DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection

One pivot challenge for image anomaly (AD) detection is to learn discriminative information only from normal class training images. Most image reconstruction based AD methods rely on the discriminative capability of reconstruction error. This is heuristic as image reconstruction is unsupervised without incorporating normal-class-specific information. In this paper, we propose an AD method called dual deep reconstruction networks based image decomposition (DDR-ID). The networks are trained by jointly optimizing for three losses: the one-class loss, the latent space constrain loss and the reconstruction loss. After training, DDR-ID can decompose an unseen image into its normal class and the residual components, respectively. Two anomaly scores are calculated to quantify the anomalous degree of the image in either normal class latent space or reconstruction image space. Thereby, anomaly detection can be performed via thresholding the anomaly score. The experiments demonstrate that DDR-ID outperforms multiple related benchmarking methods in image anomaly detection using MNIST, CIFAR-10 and Endosome datasets and adversarial attack detection using GTSRB dataset.

cs.CV↗

arXiv2020

Machine Learning and Control Theory

We survey in this article the connections between Machine Learning and Control Theory. Control Theory provide useful concepts and tools for Machine Learning. Conversely Machine Learning can be used to solve large control problems. In the first part of the paper, we develop the connections between reinforcement learning and Markov Decision Processes, which are discrete time control problems. In the second part, we review the concept of supervised learning and the relation with static optimization. Deep learning which extends supervised learning, can be viewed as a control problem. In the third part, we present the links between stochastic gradient descent and mean-field theory. Conversely, in the fourth and fifth parts, we review machine learning approaches to stochastic control problems, and focus on the deterministic case, to explain, more easily, the numerical algorithms.

cs.LG↗

arXiv2019

FaultNet: Faulty Rail-Valves Detection using Deep Learning and Computer Vision

Regular inspection of rail valves and engines is an important task to ensure the safety and efficiency of railway networks around the globe. Over the past decade, computer vision and pattern recognition based techniques have gained traction for such inspection and defect detection tasks. An automated end-to-end trained system can potentially provide a low-cost, high throughput, and cheap alternative to manual visual inspection of these components. However, such systems require a huge amount of defective images for networks to understand complex defects. In this paper, a multi-phase deep learning based technique is proposed to perform accurate fault detection of rail-valves. Our approach uses a two-step method to perform high precision image segmentation of rail-valves resulting in pixel-wise accurate segmentation. Thereafter, a computer vision technique is used to identify faulty valves. We demonstrate that the proposed approach results in improved detection performance when compared to current state-of-theart techniques used in fault detection.

cs.CV↗

arXiv2019

Improved Constructions of Coded Caching Schemes for Combination Networks

In an $(H,r)$ combination network, a single content library is delivered to ${H\choose r}$ users through deployed $H$ relays without cache memories, such that each user with local cache memories is simultaneously served by a different subset of $r$ relays on orthogonal non-interfering and error-free channels. The combinatorial placement delivery array (CPDA in short) can be used to realize a coded caching scheme for combination networks. In this paper, a new algorithm realizing a coded caching scheme for combination network based on a CPDA is proposed such that the schemes obtained have smaller subpacketization levels or are implemented more flexible than the previously known schemes. Then we focus on directly constructing CPDAs for any positive integers $H$ and $r$ with $r<H$. This is different from the grouping method in reference (IEEE ISIT, 17-22, 2018) under the constraint that $r$ divides $H$. Consequently two classes of CPDAs are obtained. Finally comparing to the schemes and the method proposed by Yan et al., (IEEE ISIT, 17-22, 2018) the schemes realized by our CPDAs have significantly advantages on the subpacketization levels and the transmission rates.

cs.IT↗