Multi-object tracking (MOT) is a critical task involving detecting and continuously tracking multiple objects within a video sequence. It is widely used in various fields, such as autonomous driving and intelligent security. In recent years, deep learning architectures have effectively promoted the development of MOT. However, this task poses significant challenges regarding accuracy due to occlusion/truncation, light variation, camera movement. Researchers have proposed many methods to address these issues to reduce trajectory fragmentation, identity switches, and missing targets. To better understand these advancements, it is essential to categorize the approaches based on their methodologies. This article reviewed the recent development of MOT, divided into Tracking by Detection (TBD) and End-to-End (E2E). By introducing and comparing the two types of tracking algorithms, readers can quickly understand the current development status of MOT. Meanwhile, this review summarizes the links to open-source code of excellent algorithms and common benchmark datasets in the appendix. And provide a unified MOT toolkit that includes evaluation and visualization at https://github.com/guanzhiyu817/MOT-tools. In addition, this review discusses the future directions of MOT, specifically cross-modal reasoning.

Cadmium (Cd) and arsenic (As) exist simultaneously in soil environment, which poses a serious threat to the safety of agricultural products and forage production. Four Perennial Ryegrass (Lolium perenne L.) cultivars with different accumulation characteristics (ʻNicaraguaʼ, ʻVenusʼ, ʻExcellentʼ and ʻMonroʼ) were selected as the material for pot experiment. The coupled responses of key components and related enzyme activities under combined stresses of Cd and As were investigated. key components contents include Non protein sulfhydryl (NPT), glutathione (GSH) and phytochelatins (PCs). The related enzyme includes (superoxide dismutase (SOD), peroxidase (POD), catalase (CAT), γ-glutamylcysteine synthetase (γ-ECS), glutathione synthetase (GSS), phytochelatin synthetases (PCSase) and arsenate reductase (AR). The results showed that Cd contents of perennial ryegrass were higher than those of As contents with TF_Cd/As < 1. Cd and As contents in roots were in the higher proportion than those in shoots. Compared to control, POD activities increased by 2.72 folds under 120 mg kg⁻¹ As treatment. The contents of PCs increased by 5.68 folds under 120 mg kg⁻¹ As treatment. Under combined Cd and As stress, the MDA contents and antioxidant enzyme activities of ʻVenusʼ were higher than those of ʻNicaraguaʼ. ʻNicaraguaʼ, a high accumulation cultivar. Under the combined stresses of Cd and As, the enzyme activities and the key components were significantly correlated (P < 0.05) with the contents of Cd and As. The tolerance to Cd and As was improved with increase in GSH and PCs contents and γ-ECS, GSS, PCSase and AR activities. In conclusion, the antioxidant enzyme system and key resistant substances of perennial ryegrass have important and antagonistic effects on Cd and As stresses.

Automated detection of road damage (ADRD) is a challenging topic in road maintenance. It focuses on automatically detecting road damage and assessing severity by deep learning. Because of the sparse distribution of characteristic pixels, it is more challenging than object detection. Although some public datasets provide a database for the development of ADRD, their amounts of data and the standard of classification cannot meet network training and feature learning. With the aim of solving this problem, this work publishes a new road damage dataset named CNRDD, which is labeled according to the latest evaluation standard for highway technical conditions in China (JTG5210-2018). The dataset is collected by professional onboard cameras and is manually labeled in eight categories with three different degrees (mild, moderate and severe), which can effectively help promote research of automated detection of road damage. At the same time, a novel baseline with attention fusion and normalization is proposed to evaluate and analyze the published dataset. It explicitly leverages edge detection cues to guide attention for salient regions and suppresses the weights of non-salient features by attention normalization, which can alleviate the interference of sparse pixel distribution on damage detection. Experimental results demonstrate that the proposed baseline significantly outperforms most existing methods on the existing RDD2020 dataset and the newly released CNRDD dataset. Further, the CNRDD dataset is proved more robust, as its high damage density and professional classification are more conducive to promote the development of ADRD.

Sign language recognition has been utilized in human–machine interactions, improving the lives of people with speech impairments or who rely on nonverbal instructions. Thanks to its higher temporal resolution, less visual redundancy information and lower energy consumption, the use of an event camera with a new dynamic vision sensor (DVS) shows promise with regard to sign language recognition with robot perception and intelligent control. Although previous work has focused on event camera-based, simple gesture datasets, such as DVS128Gesture, event camera gesture datasets inspired by sign language are critical, which poses a great impediment to the development of event camera-based sign language recognition. An effective method to extract spatio-temporal features from event data is significantly desired. Firstly, the event-based sign language gesture datasets are proposed and the data have two sources: traditional sign language videos to event stream (DVS_Sign_v2e) and DAVIS346 (DVS_Sign). In the present dataset, data are divided into five classification, verbs, quantifiers, position, things and people, adapting to actual scenarios where robots provide instruction or assistance. Sign language classification is demonstrated in spike neuron networks with a spatio-temporal back-propagation training method, leading to the best recognition accuracy of 77%. This work paves the way for the combination of event camera-based sign language gesture recognition and robotic perception for the future intelligent systems.

Person/vehicle re‐identification aims to use technologies such as cross‐camera retrieval to associate the same person (same vehicle) in the surveillance videos at different locations, different times, and images captured by different cameras so as to achieve cross‐surveillance image matching, person retrieval and trajectory tracking. It plays an extremely important role in the fields of intelligent security, criminal investigation etc. In recent years, the rapid development of deep learning technology has significantly propelled the advancement of re‐identification (Re‐ID) technology. An increasing number of technical methods have emerged, aiming to enhance Re‐ID performance. This paper summarises four popular research areas in the current field of re‐identification, focusing on the current research hotspots. These areas include the multi‐task learning domain, the generalisation learning domain, the cross‐modality domain, and the optimisation learning domain. Specifically, the paper analyses various challenges faced within these domains and elaborates on different deep learning frameworks and networks that address these challenges. A comparative analysis of re‐identification tasks from various classification perspectives is provided, introducing mainstream research directions and current achievements. Finally, insights into future development trends are presented.