Table 3 Keynote of studies that were used to address the research question on main Action Recognition techniques and applications in autonomous transportation

Yao et al. [86]

The researchers developed a benchmark dataset to assess the quality of traffic accident detection and anomaly detection for nine action classes

Yu et al. [23]

Traffic accidents can be caused by many factors, including driver behavior, weather conditions, traffic flow, and road structures. The authors investigated spatial–temporal relationships on heterogeneous data to develop a road-level accident prediction system

Wang et al. [80]

The goal of this project is to develop a framework for analyzing stationary time series traffic data. In addition, it is able to predict traffic information with a 14.1% improvement in MAPE compared to other baselines

Bao et al. [88]

Using GCN and BNN, the developed model can handle the challenges of relational feature learning and uncertainty anticipation from video data to anticipate an accident in 3.53 s with an average precision of 72.22%

Reddy et al. [26]

The research investigates how to extract road features relevant to the trajectory of an autonomous vehicle from real-world road conditions using Deep Q-Learning in a real-world environment setting

Fernandez et al. [84]

This study utilized a visual cue derived from a camera to detect lane change/vehicle maneuvers by utilizing a disjoint two-stream convolutional network and a spatiotemporal multiplier network

Ali et al. [22]

The authors propose a hybrid model combining GCN and DHSTNet that is effective in forecasting short-term traffic patterns in urban areas in order to improve traffic management

Wang et al. [21]

The researchers developed a new dataset and proposed a method for safety prediction

Alkandari et al. [89]

The main aim of this study is to develop a methodology for controlling the length of time that a vehicle stays in traffic based on the flow of traffic and congestion

Riaz et al. [90]

This study implemented the FWPredNet framework for accident and anomaly prediction, which outperformed the previous state-of-the-art framework

Tang et al. [91]

Researchers developed a framework for conceptually describing components of surveillance video, separating them into smaller components, and detecting activities from some short clips of two seconds

Huang et al. [25]

The authors present a comparative analysis of different statistical and deep learning models for solving traffic safety problems through the detection of collisions and estimating crash risk in urban Interstate highways

Bortnikov et al. [92]

Through the use of video games under different weather conditions and scene conditions, the study generated traffic data that was then processed and trained with a 3D CNN. This model yielded comparable results to real-life traffic videos from YouTube

Gupta et al. [93]

Using time-dependent frames in a video, the developed model was able to evaluate the effectiveness of the model on trimmed unlabeled video

Yang et al. [94]

In this paper, researchers propose developing a feature-fused SSD in order to improve detection accuracy of vehicles from the ImageNet video database

Ijjina et al. [83]

The proposed supervised deep learning framework detects and identifies road-side vehicular accidents by extracting feature points based on local features such as trajectory intersection and velocity, and by detecting anomalies in real-time accident conditions such as daylight variations

You et al. [85]

In this study, the authors discovered that time segmentation methods such as SS-TCN and MS-TCN were more successful on the dataset at higher IoU thresholds. In addition, the R-C3D algorithm has a comparable result when compared to segmentation-based approaches

Srinivasan et al. [24]

The authors developed a scalable algorithm for high-speed object detection (DETR), with a less complex architecture and a higher level of accuracy compared to other object detection algorithms that are based on correlations between all objects in the video data

Hui et al. [95]

The authors proposed using a Gaussian Mixture Model to extract foreground and background information from video streams in order to create a vision-based accident detection model

Min et al. [87]

The authors applied the SIFT flow method to improve dense trajectories and generate visual words that can be utilized in detecting traffic flow. The data from the experiments demonstrate that the SIFT method is effective

Vatti et al. [96]

The authors developed an electronic notification system that can alert relatives when a vehicle accident is detected based on the vehicle's trajectory, position, and acceleration