GiT: Graph Interactive Transformer for Vehicle Re-identification

Rethinking Attention Mechanisms in Vision Transformers with Graph Structures

In this paper, we propose a new type of vision transformer (ViT) based on graph head attention (GHA). Because the multi-head attention (MHA) of a pure ViT requires multiple parameters and tends to lose the locality of an image, we replaced MHA with GHA by applying a graph to the attention head of the transformer. Consequently, the proposed GHA maintains both the locality and globality of the input patches and guarantees the diversity of the attention. The proposed GHA-ViT commonly outperforms pure ViT-based models using small-sized CIFAR-10/100, MNIST, and MNIST-F datasets and a medium-sized ImageNet-1K dataset in scratch training. A Top-1 accuracy of 81.7% was achieved for ImageNet-1K using GHA-B, which is a base model with approximately 29 M parameters. In addition, with CIFAR-10/100, the existing ViT and parameters are reduced 17-fold and the performance increased by 0.4/4.3%, respectively. The proposed GHA-ViT shows promising results in terms of the number of parameters and operations and the level of accuracy in comparison with other state-of-the-art ViT-lightweight models.

A novel dual-pooling attention module for UAV vehicle re-identification

Vehicle re-identification (Re-ID) involves identifying the same vehicle captured by other cameras, given a vehicle image. It plays a crucial role in the development of safe cities and smart cities. With the rapid growth and implementation of unmanned aerial vehicles (UAVs) technology, vehicle Re-ID in UAV aerial photography scenes has garnered significant attention from researchers. However, due to the high altitude of UAVs, the shooting angle of vehicle images sometimes approximates vertical, resulting in fewer local features for Re-ID. Therefore, this paper proposes a novel dual-pooling attention (DpA) module, which achieves the extraction and enhancement of locally important information about vehicles from both channel and spatial dimensions by constructing two branches of channel-pooling attention (CpA) and spatial-pooling attention (SpA), and employing multiple pooling operations to enhance the attention to fine-grained information of vehicles. Specifically, the CpA module operates between the channels of the feature map and splices features by combining four pooling operations so that vehicle regions containing discriminative information are given greater attention. The SpA module uses the same pooling operations strategy to identify discriminative representations and merge vehicle features in image regions in a weighted manner. The feature information of both dimensions is finally fused and trained jointly using label smoothing cross-entropy loss and hard mining triplet loss, thus solving the problem of missing detail information due to the high height of UAV shots. The proposed method's effectiveness is demonstrated through extensive experiments on the UAV-based vehicle datasets VeRi-UAV and VRU.

GLFNet: Combining Global and Local Information in Vehicle Re-Recognition

Vehicle re-identification holds great significance for intelligent transportation and public safety. Extracting vehicle recognition information from multi-view vehicle images has become one of the challenging problems in the field of vehicle recognition. Most recent methods employ a single network extraction structure, either a single global or local measure. However, for vehicle images with high intra-class variance and low inter-class variance, exploring globally invariant features and discriminative local details is necessary. In this paper, we propose a Feature Fusion Network (GLFNet) that combines global and local information. It utilizes global features to enhance the differences between vehicles and employs local features to compactly represent vehicles of the same type. This enables the model to learn features with a large inter-class distance and small intra-class distance, significantly improving the model's generalization ability. Experiments show that the proposed method is competitive with other advanced algorithms on three mainstream road traffic surveillance vehicle re-identification benchmark datasets.

SegT: Separated edge-guidance transformer network for polyp segmentation

Accurate segmentation of colonoscopic polyps is considered a fundamental step in medical image analysis and surgical interventions. Many recent studies have made improvements based on the encoder-decoder framework, which can effectively segment diverse polyps. Such improvements mainly aim to enhance local features by using global features and applying attention methods. However, relying only on the global information of the final encoder block can result in losing local regional features in the intermediate layer. In addition, determining the edges between benign regions and polyps could be a challenging task. To address the aforementioned issues, we propose a novel separated edge-guidance transformer (SegT) network that aims to build an effective polyp segmentation model. A transformer encoder that learns a more robust representation than existing convolutional neural network-based approaches was specifically applied. To determine the precise segmentation of polyps, we utilize a separated edge-guidance module consisting of separator and edge-guidance blocks. The separator block is a two-stream operator to highlight edges between the background and foreground, whereas the edge-guidance block lies behind both streams to strengthen the understanding of the edge. Lastly, an innovative cascade fusion module was used and fused the refined multi-level features. To evaluate the effectiveness of SegT, we conducted experiments with five challenging public datasets, and the proposed model achieved state-of-the-art performance.

Metric networks for enhanced perception of non-local semantic information

Introduction

Metric learning, as a fundamental research direction in the field of computer vision, has played a crucial role in image matching. Traditional metric learning methods aim at constructing two-branch siamese neural networks to address the challenge of image matching, but they often overlook to cross-source and cross-view scenarios.

Methods

In this article, a multi-branch metric learning model is proposed to address these limitations. The main contributions of this work are as follows: Firstly, we design a multi-branch siamese network model that enhances measurement reliability through information compensation among data points. Secondly, we construct a non-local information perception and fusion model, which accurately distinguishes positive and negative samples by fusing information at different scales. Thirdly, we enhance the model by integrating semantic information and establish an information consistency mapping between multiple branches, thereby improving the robustness in cross-source and cross-view scenarios.

Results

Experimental tests which demonstrate the effectiveness of the proposed method are carried out under various conditions, including homologous, heterogeneous, multi-view, and crossview scenarios. Compared to the state-of-the-art comparison algorithms, our proposed algorithm achieves an improvement of ~1, 2, 1, and 1% in terms of similarity measurement Recall@10, respectively, under these four conditions.

Discussion

In addition, our work provides an idea for improving the crossscene application ability of UAV positioning and navigation algorithm.

Multi-Object Multi-Camera Tracking Based on Deep Learning for Intelligent Transportation: A Review

Multi-Objective Multi-Camera Tracking (MOMCT) is aimed at locating and identifying multiple objects from video captured by multiple cameras. With the advancement of technology in recent years, it has received a lot of attention from researchers in applications such as intelligent transportation, public safety and self-driving driving technology. As a result, a large number of excellent research results have emerged in the field of MOMCT. To facilitate the rapid development of intelligent transportation, researchers need to keep abreast of the latest research and current challenges in related field. Therefore, this paper provide a comprehensive review of multi-object multi-camera tracking based on deep learning for intelligent transportation. Specifically, we first introduce the main object detectors for MOMCT in detail. Secondly, we give an in-depth analysis of deep learning based MOMCT and evaluate advanced methods through visualisation. Thirdly, we summarize the popular benchmark data sets and metrics to provide quantitative and comprehensive comparisons. Finally, we point out the challenges faced by MOMCT in intelligent transportation and present practical suggestions for the future direction.

Hybrid framework for single-pointer meter identification

Automated identification of single-pointer meter identification in substations is widely used in the construction of digital substations and it must accurately identify the value of the pointer meter. Current single-pointer meter identification methods are not universally applicable and can only identify one type of meter. In this study, we present a hybrid framework for single-pointer meter identification. First, the input image of the single-pointer meter is modeled to gain a priori knowledge, including the template image, dial position information, the pointer template image, and scale value positions. Based on a convolutional neural network to generate the input image and the template image feature points, image alignment is then applied through a feature point match to mitigate slight changes in the camera angle. Next, a pixel loss-free method of arbitrary point image rotation correction is presented for rotation template matching. Finally, by rotating the input gray mask image of the dial and matching it to the pointer template to get the optimal rotation angle, the meter value is calculated. The experimental findings demonstrate the method's effectiveness in identifying nine different types of single-pointer meters in substations with various ambient illuminations. This study provides a feasible reference for substations to identify the value of different types of single-pointer meters.