Scatterplots are widely used in Explainable Artificial Intelligence (XAI) to investigate misclassifications and patterns across instances. However, a significant limitation of scatterplots is overplotting, especially when working with large datasets. Although several quality metrics have been proposed to measure the degree of overplotting, none have been demonstrated to be effective in the context of XAI. This paper aims to evaluate the effectiveness of a quality metric, called OM4AnI, in XAI scenarios. We begin by summarizing two visual patterns—cluster-based and regression-based patterns—that support three common XAI tasks: feature importance, feature dependency, and model accuracy. We also introduce how to select the parameters of OM4AnI based on these patterns. We construct two case studies to identify the effectiveness of OM4AnI using public datasets: Census Income dataset and MNIST dataset. OM4AnI is applied to both scenarios under various visual conditions (e.g., marker size and rendering order) to assess its effectiveness. The results demonstrate that OM4AnI serves as an effective quality metric for these two common XAI scenarios, paving the way for adapting other quality metrics to be scalable within XAI contexts.

Scatterplots are widely used across various domains to identify anomalies in datasets, particularly in multi-class settings, such as detecting misclassified or mislabeled data. However, scatterplot effectiveness often declines with large datasets due to limited display resolution. This paper introduces a novel Visual Quality Measure (VQM) - OM4AnI (Overlap Measure for Anomaly Identification) - which quantifies the degree of overlap for identifying anomalies, helping users estimate how effectively anomalies can be observed in multi-class scatterplots. OM4AnI begins by computing anomaly index based on each data point's position relative to its class cluster. The scatterplot is then discretized into a matrix representation by binning the display space into cell-level (pixel-level) grids and computing the coverage for each pixel. It takes into account the anomaly index of data points covering these pixels and visual features (marker shapes, marker sizes, and rendering orders). Building on this foundation, we sum all the coverage information in each cell (pixel) of matrix representation to obtain the final quality score with respect to anomaly identification. We conducted an evaluation to analyze the efficiency, effectiveness, sensitivity of OM4AnI in comparison with six representative baseline methods that are based on different computation granularity levels: data level, marker level, and pixel level. The results show that OM4AnI outperforms baseline methods by exhibiting more monotonic trends against the ground truth and greater sensitivity to rendering order, unlike the baseline methods. It confirms that OM4AnI can inform users about how effectively their scatterplots support anomaly identification. Overall, OM4AnI shows strong potential as an evaluation metric and for optimizing scatterplots through automatic adjustment of visual parameters.

Prediction of pedestrian crossing intention is a critical function in autonomous vehicles. Conventional vision-based methods of crossing intention prediction often struggle with generalizability, context understanding, and causal reasoning. This study explores the potential of vision-language foundation models (VLFMs) for predicting pedestrian crossing intentions by integrating multimodal data through hierarchical prompt templates. The methodology incorporates contextual information, including visual frames, physical cues observations, and ego-vehicle dynamics, into systematically refined prompts to guide VLFMs effectively in intention prediction. Experiments were conducted on three common datasets—JAAD, PIE, and FU-PIP. Results demonstrate that incorporating vehicle speed, its variations over time, and time-conscious prompts significantly enhances the prediction accuracy up to 19.8%. Additionally, optimised prompts generated via an automatic prompt engineering framework yielded 12.5% further accuracy gains. These findings highlight the superior performance of VLFMs compared to conventional vision-based models, offering enhanced generalisation and contextual understanding for autonomous driving applications.

Ensuring safe transition of control in automated vehicles requires an accurate and timely assessment of driver readiness. This paper introduces Driver-Net, a novel deep learning framework that fuses multi-camera inputs to estimate driver take-over readiness. Unlike conventional vision-based driver monitoring systems that focus on head pose or eye gaze, Driver-Net captures synchronised visual cues from the driver's head, hands, and body posture through a triple-camera setup. The model integrates spatio-temporal data using a dual-path architecture, comprising a Context Block and a Feature Block, followed by a cross-modal fusion strategy to enhance prediction accuracy. Evaluated on a diverse dataset collected from the University of Leeds Driving Simulator, the proposed method achieves an accuracy of up to 95.8% in driver readiness classification. This performance significantly enhances existing approaches and highlights the importance of multimodal and multi-view fusion. As a real-time, non-intrusive solution, Driver-Net contributes meaningfully to the development of safer and more reliable automated vehicles and aligns with new regulatory mandates and upcoming safety standards.

Accurate pedestrian intention prediction (PIP) by Autonomous Vehicles (AVs) is one of the current research challenges in this field. In this article, we introduce PIP-Net, a novel framework designed to predict pedestrian crossing intentions by AVs in real-world urban scenarios. We offer two variants of PIP-Net designed for different camera mounts and setups. Leveraging both kinematic data and spatial features from the driving scene, the proposed model employs a recurrent and temporal attention-based solution, outperforming state-of-the-art performance. To enhance the visual representation of road users and their proximity to the ego vehicle, we introduce a categorical depth feature map, combined with a local motion flow feature, providing rich insights into the scene dynamics. Additionally, we explore the impact of expanding the camera’s field of view, from one to three cameras surrounding the ego vehicle, leading to an enhancement in the model’s contextual perception. Depending on the traffic scenario and road environment, the model excels in predicting pedestrian crossing intentions up to 4 seconds in advance, which is a breakthrough in current research studies in pedestrian intention prediction. Finally, for the first time, we present the Urban-PIP dataset, a customised pedestrian intention prediction dataset, with multi-camera annotations in real-world automated driving scenarios.

Multi-task learning in advanced driver assistance systems aims to endow models with the capacity to jointly handle multiple related tasks, such as object detection, depth estimation, and more. However, existing multi-task learning models largely rely on the extensive number of labelled data. In practice, the process of annotating data for multi-task training proves to be exceedingly costly, yet not always accurate. This study introduces an innovative setting named online multi-task inference learning that updates the multi-task model during inference. And we propose a Strong-Help-Weak (SHW) framework which aims to enhance weaker (or more challenging) tasks by leveraging guidance from closely related stronger (or easier) tasks. Specifically, we first build two benchmarks based on KITTI and BDD with four tasks (object detection, object depth estimation, lane line segmentation, and driving area segmentation). Then, we propose two novel modules inspired by two priors: 1) Detection-guided Depth Inference Learning (DetDis) module that leverages the inverse relationship between object size and distance to refine the predicted object distance; and 2) Area-guided Lane Line Inference Learning (AreaLane) module that utilises inclusion relationship between driving area and lane line to infer more accurate lane line. Both modules are efficient and can provide more reliable supervision for the corresponding weaker tasks (object distance estimation and lane line segmentation), respectively. Extensive experiments on the two benchmarks show that our SHW can obtain consistent improvements on the weaker tasks during the inference stage with low computational costs.

Machine Learning has played a major role in various applications including Autonomous Vehicles and Intelligent Transportation Systems. Utilizing a deep convolutional neural network, the article introduces a zero-calibration 3D Object recognition and tracking system for traffic monitoring. The model can accurately work on urban traffic cameras, regardless of their technical specification (i.e. resolution, lens, the field of view) and positioning (location, height, angle). For the first time, we introduce a novel satellite-ground inverse perspective mapping technique, which requires no camera calibrations and only needs the GPS position of the camera. This leads to an accurate environmental modeling solution that is capable of estimating road users’ 3D bonding boxes, speed, and trajectory using a monocular camera. We have also contributed to a hierarchical activity/traffic modeling solution using short- and long-term Spatio-temporal video analysis to understand the heatmap of the traffic flow, bottlenecks, and high-risk zones. The experiments are conducted on four datasets: MIO-TCD, UA-DETRAC, GRAM-RTM, and Leeds-Dataset including various use cases and traffic scenarios.

Scene understanding plays a crucial role in autonomous driving by utilizing sensory data for contextual information extraction and decision making. Beyond modeling advances, the enabler for vehicles to become aware of their surroundings is the availability of visual sensory data, which expand the vehicular perception and realizes vehicular contextual awareness in real-world environments. Research directions for scene understanding pursued by related studies include person/vehicle detection and segmentation, their transition analysis, lane change, and turns detection, among many others. Unfortunately, these tasks seem insufficient to completely develop fully-autonomous vehicles i.e., achieving level-5 autonomy, travelling just like human-controlled cars. This latter statement is among the conclusions drawn from this review paper: scene understanding for autonomous driving cars using vision sensors still requires significant improvements. With this motivation, this survey defines, analyzes, and reviews the current achievements of the scene understanding research area that mostly rely on computationally complex deep learning models. Furthermore, it covers the generic scene understanding pipeline, investigates the performance reported by the state-of-the-art, informs about the time complexity analysis of avant garde modeling choices, and highlights major triumphs and noted limitations encountered by current research efforts. The survey also includes a comprehensive discussion on the available datasets, and the challenges that, even if lately confronted by researchers, still remain open to date. Finally, our work outlines future research directions to welcome researchers and practitioners to this exciting domain.

In this paper, we present an active vision method using a deep reinforcement learning approach for a humanoid soccer-playing robot. The proposed method adaptively optimises the viewpoint of the robot to acquire the most useful landmarks for self-localisation while keeping the ball into its viewpoint. Active vision is critical for humanoid decision-maker robots with a limited field of view. To deal with an active vision problem, several probabilistic entropy-based approaches have previously been proposed which are highly dependent on the accuracy of the self-localisation model. However, in this research, we formulate the problem as an episodic reinforcement learning problem and employ a Deep Q-learning method to solve it. The proposed network only requires the raw images of the camera to move the robot's head toward the best viewpoint. The model shows a very competitive rate of 80% success rate in achieving the best viewpoint. We implemented the proposed method on a humanoid robot simulated in Webots simulator. Our evaluations and experimental results show that the proposed method outperforms the entropy-based methods in the RoboCup context, in cases with high self-localisation errors.

This paper highlights the role of ground manifold modeling for stixel calculations; stixels are medium-level data representations used for the development of computer vision modules for self-driving cars. By using single-disparity maps and simplifying ground manifold models, calculated stixels may suffer from noise, inconsistency, and false-detection rates for obstacles, especially in challenging datasets. Stixel calculations can be improved with respect to accuracy and robustness by using more adaptive ground manifold approximations. A comparative study of stixel results, obtained for different ground-manifold models (e.g., plane-fitting, line-fitting in v-disparities or polynomial approximation, and graph cut), defines the main part of this paper. This paper also considers the use of trinocular stereo vision and shows that this provides options to enhance stixel results, compared with the binocular recording. Comprehensive experiments are performed on two publicly available challenging datasets. We also use a novel way for comparing calculated stixels with ground truth. We compare depth information, as given by extracted stixels, with ground-truth depth, provided by depth measurements using a highly accurate LiDAR range sensor (as available in one of the public datasets). We evaluate the accuracy of four different ground-manifold methods. The experimental results also include quantitative evaluations of the tradeoff between accuracy and run time. As a result, the proposed trinocular recording together with graph-cut estimation of ground manifolds appears to be a recommended way, also considering challenging weather and lighting conditions.

Avoiding high computational costs and calibration issues involved in stereo-vision-based algorithms, this paper proposes real-time monocular-vision-based techniques for simultaneous vehicle detection and inter-vehicle distance estimation, in which the performance and robustness of the system remain competitive, even for highly challenging benchmark datasets. This paper develops a collision warning system by detecting vehicles ahead and, by identifying safety distances to assist a distracted driver, prior to occurrence of an imminent crash. We introduce adaptive global Haar-like features for vehicle detection, tail-light segmentation, virtual symmetry detection, intervehicle distance estimation, as well as an efficient single-sensor multifeature fusion technique to enhance the accuracy and robustness of our algorithm. The proposed algorithm is able to detect vehicles ahead at both day or night and also for short- and long-range distances. Experimental results under various weather and lighting conditions (including sunny, rainy, foggy, or snowy) show that the proposed algorithm outperforms state-of-the-art algorithms.

The paper proposes an advanced driver-assistance system that correlates the driver's head pose to road hazards by analyzing both simultaneously. In particular, we aim at the prevention of rear-end crashes due to driver fatigue or distraction. We contribute by three novel ideas: Asymmetric appearance-modeling, 2D to 3D pose estimation enhanced by the introduced Fermat-point transform, and adaptation of Global Haar (GHaar) classifiers for vehicle detection under challenging lighting conditions. The system defines the driver's direction of attention (in 6 degrees of freedom), yawning and head-nodding detection, as well as vehicle detection, and distance estimation. Having both road and driver's behaviour information, and implementing a fuzzy fusion system, we develop an integrated framework to cover all of the above subjects. We provide real-time performance analysis for real-world driving scenarios.