Department Publications

Vehicle license plate recognition is an integral component of intelligent transportation systems. In this work, we present an embedded real-time license plate recognition system customized for developing countries. We address the challenge of handling complex, unstructured traffic scenes with diverse vehicle types while implementing the system on an embedded platform for low-cost deployment. Our method consists of license plate detection on a multi-vehicle image, followed by character recognition on the detected license plates. Both steps use lightweight convolutional neural networks to balance accuracy and efficiency. We also introduce the SL-LPR dataset of Sri Lankan road images, which contains a variety of vehicle types and traffic conditions typically seen in developing countries. On this dataset, the license plate detection and character recognition models achieved 93.6% mAP and 87.88% accuracy, respectively, and were competitive against larger models on several public datasets. To achieve real-time performance in a resource-constrained embedded environment, we applied low-bitwidth quantization using the Brevitas library and implemented FPGA acceleration for the models using the FINN framework. The end-to-end system can operate at 11.5~FPS when implemented on the Xilinx Kria KV260 platform. These results demonstrate that our system is effective for real-time license plate recognition on an embedded device, even in complex traffic scenarios. The SL-LPR dataset is available for research use at: https://github.com/sl-lpr-uom/SL-LPR.git.

Traffic signal design in developing countries frequently underperforms due to the direct application of classical models—Webster's delay formula, HCM, ARR123, and ORN13—developed for homogeneous, lane-disciplined traffic conditions. Sri Lankan intersections exhibit fundamentally different characteristics: heterogeneous vehicle streams comprising motorcycles, three-wheelers, non-motorized vehicles, and pedestrians operating without strict lane discipline under geometric constraints. This systematic review synthesizes empirical evidence explaining why conventional signal design methods fail in such contexts. Following PRISMA principles, 138 records were screened, yielding 41 high-quality references spanning foundational theory, classical assumptions, regional adaptations, and Sri Lankan empirical data. The review demonstrates that local intersections systematically violate foundational assumptions regarding lane usage, headway uniformity, start-up behavior, and pedestrian compliance. Observed saturation flows reach 2574 pcu/h/lane—substantially exceeding HCM benchmarks—while behaviors such as motorcycle seepage, lateral filtering, initial surge, and dynamic clustering create discharge patterns that static PCU values cannot capture. A mathematical framework is presented mapping these deviations to quantifiable variables: lateral efficiency, surge discharge dynamics, dynamic vehicle equivalence, headway expansion, and geometric constraints affecting intersection capacity. The paper concludes by proposing context-sensitive design pathways incorporating dynamic PCU factors, behavioral modeling, and simulation …

Real-time pedestrian sensing at crossings is essential for Intelligent Transportation Systems (ITS). Yet traditional vision-based solutions and wearable devices face privacy, cost, and deployment challenges. While Wi-Fi channel state information (CSI) has shown promise in indoor environments, its potential for dynamic outdoor environments remains largely unexplored. This paper presents a device-free, CSI-based system for detecting human movement and walking direction at crossings and alert oncoming vehicles to enhance pedestrian safety. A twostage classification framework is adopted with noise suppression and Doppler-sensitive features. Classical and deep learning models are evaluated across four outdoor locations and seven subjects, achieving 96.9% accuracy for movement detection and up to 62% accuracy for classification of movement direction. These findings demonstrate the feasibility of …

Vehicular ad-hoc networks (VANETs) face significant challenges in channel estimation, primarily due to the rapidly changing environment and the impact of Doppler frequency shifts caused by high-speed vehicle movement. This paper aims to evaluate the performance of existing channel estimation algorithms under scenarios with Doppler frequency shifts through computational experiments, with the assessment metric being the bit error rate (BER) performance of the algorithms under various signal-to-noise ratio (SNR) conditions. Based on simulation results, this paper systematically compares the effects of the least squares (LS), linear minimum mean square error (LMMSE), radial basis function (RBF), and genetic algorithm-optimized RBF (GA-RBF) in both relay-free and relayed scenarios, assessing their effectiveness in low-speed and high-speed environments. The results show that the LMMSE and GA-RBF …

Maritime surveillance is vital to mitigate illegal activities such as drug smuggling, illegal fishing, and human trafficking. Vision-based maritime surveillance is challenging mainly due to visibility issues at night, which results in failures in re-identifying vessels and detecting suspicious activities. In this paper, we introduce a thermal, vision-based approach for maritime surveillance with object tracking, vessel re-identification, and suspicious activity detection capabilities. For vessel re-identification, we propose a novel viewpoint-independent algorithm which compares features of the sides of the vessel separately (separate side-spaces) leveraging shape information in the absence of color features. We propose techniques to adapt tracking and activity detection algorithms for the thermal domain and train them using a thermal dataset we created. This dataset will be the first publicly available benchmark dataset for thermal maritime surveillance. Our system is capable of re-identifying vessels with an 81.8% Top1 score and identifying suspicious activities with a 72.4\% frame mAP score; a new benchmark for each task in the thermal domain.

We present SimuSIL, a software-in-the-loop (SIL) simulation platform using open-source tools to capture the behavior of connected vehicles in intelligent transportation system (ITS) applications. Connected cooperative vehicles use vehicle-to-everything (V2X) communication to enable ITS. Real-world testing of ITS applications involves significant risks. Simulating true vehicle dynamics and real-time behavior is challenging in discrete time step environments. We extend the Veins platform, integrating SUMO and OMNet++, with Webots, a simulator for robots and vehicles. Webots implements engine control unit (ECU) models in software to mimic physical vehicle behavior. We validate SimuSIL with a car-following application using Webots and demonstrate its ability to capture communication anomalies like packet losses. Additionally, we demonstrate fuel consumption and CO 2 emissions in autonomous eco-driving …

The ability to accurately localize vehicles is essential for driver assistance applications. Existing modern localization systems, while sophisticated, often come with considerable costs and limitations in accessibility. Recognizing the need for a more accessible solution, there is a growing demand for user-friendly and cost-effective alternatives. One such alternative lies in leveraging mobile devices for localization. However, relying solely on Global Positioning System (GPS), Wi-Fi, or cellular networks, the most commonly used technologies in mobile device localization, often suffer from issues with accuracy. Addressing these drawbacks is crucial to ensuring its effectiveness and widespread adoption. Map matching is a commonly pursued and well-researched approach taken to rectify these erroneous location data. This paper presents the implementation of a hybrid of two map-matching implementations on a mobile …

Prioritization of data streams in cellular vehicle-to-everything (C-V2X) may lead to unfavorable packet delays in low-priority streams. This paper studies allocating multiple candidate single-subframe resources (CSRs) per vehicle as a solution. It proposes a methodology to determine the number of CSRs for each vehicle based on the total number of neighboring vehicles, and to assign the multiple data streams among them for simultaneous transmission. The numerical results highlight the achievable delay gains of the proposed approach, and its negligible impact on packet collisions.

Traffic light detection is essential for self-driving cars to navigate safely in urban areas. Publicly available traffic light datasets are inadequate for the development of algorithms for detecting distant traffic lights that provide important navigation information. We introduce a novel bench-mark traffic light dataset captured using a synchronized pair of narrow-angle and wide-angle cameras covering urban and semi-urban roads. We provide 1032 images for training and 813 synchronized image pairs for testing. Additionally, we provide synchronized test video pairs for qualitative analysis. The dataset includes images of resolution covering 10 different classes. Furthermore, we propose a post-processing algorithm for combining outputs from the two cameras. Results show that our technique can strike a balance between speed and accuracy, compared to the conventional approach of using a single camera frame …

Traffic management is a serious problem in many cities around the world. Even the suburban areas are now experiencing regular traffic congestion. Inappropriate traffic control wastes fuel, time, and the productivity of nations. Though traffic signals are used to improve traffic flow, they often cause problems due to inappropriate or obsolete timing that does not tally with the actual traffic intensity at the intersection. Traffic intensity determination based on statistical methods only gives the average intensity expected at any given time. However, to control traffic accurately, it is required to know the real-time traffic intensity. In this research, image processing and machine learning have been used to estimate actual traffic intensity in real time. General-purpose electronic hardware has been used for in-situ image processing based on the edge-detection method. A deep neural network (DNN) was trained to infer traffic intensity in each image in real time. The trained DNN estimated traffic intensity accurately in 90% of the real-time images during road tests. The electronic system was implemented on a Raspberry Pi single-board computer; hence, it is cost-effective for large-scale deployment.

In this paper, we introduce a novel road marking bench-mark dataset for road marking detection, addressing the limitations in the existing publicly available datasets such as lack of challenging scenarios, prominence given to lane markings, unavailability of an evaluation script, lack of an-notation formats and lower resolutions. Our dataset consists of 2887 total images with 4706 road marking instances belonging to 11 classes. The images have a high resolution of 1920 × 1080 and capture a wide range of traffic, lighting and weather conditions. We provide road marking an-notations in polygons, bounding boxes and pixel-level segmentation masks to facilitate a diverse range of road marking detection algorithms. The evaluation metrics and the evaluation script we provide, will further promote direct comparison of novel approaches for road marking detection with existing methods. Furthermore, we evaluate the …

Recent work done on traffic sign and traffic light detection focus on improving detection accuracy in complex scenarios, yet many fail to deliver real-time performance, specifically with limited computational resources. In this work, we propose a simple deep learning based end-to-end detection framework, which effectively tackles challenges inherent to traffic sign and traffic light detection such as small size, large number of classes and complex road scenarios. We optimize the detection models using TensorRT and integrate with Robot Operating System to deploy on an Nvidia Jetson AGX Xavier as our embedded device. The overall system achieves a high inference speed of 63 frames per second, demonstrating the capability of our system to perform in real-time. Furthermore, we introduce CeyRo, which is the first ever large-scale traffic sign and traffic light detection dataset for the Sri Lankan context. Our dataset …

Penetration of Intelligent Transport Systems (ITS) applications is slow, particularly in developing countries, mainly due to the costs associated with the two state-of-the-art technologies, Dedicated Short-Range Communication (DSRC) and Cellular-V2x (c-V2x).As a solution, this paper presents a DSRC/Wi-Fi hybrid system and evaluates its performance experimentally. Communication within the Wi-Fi segment is via customized beacons serving a similar function as roadside alerts in DSRC, but with a configurable repetition interval. The results show that Wi-Fi beacons can be received over a 200m range with a packet delivery rate of more than 50%. Considering the effective range and the information update rate, we illustrate several applications that are feasible with the hybrid system in Vehicle-to-Vehicle (V2V) and Infrastructure-to-Vehicle (I2V) modes. With our novel hardware design, the expected functionality can …

Predicting the possible future trajectories of the surrounding dynamic agents is an essential requirement in autonomous driving. These trajectories mainly depend on the surrounding static environment, as well as the past movements of those dynamic agents. Furthermore, the multimodal nature of agent intentions makes the trajectory prediction problem more challenging. All of the existing models consider the target agent as well as the surrounding agents similarly, without considering the variation of physical properties. In this paper, we present a novel deep-learning based framework for multimodal trajectory prediction in autonomous driving, which considers the physical properties of the target and surrounding vehicles such as the object class and their physical dimensions through a weighted attention module, that improves the accuracy of the predictions. Our model has achieved the highest results in the nuScenes trajectory prediction benchmark, out of the models which use rasterized maps to input environment information. Furthermore, our model is able to run in real-time, achieving a high inference rate of over 300 FPS.

Recent work done on lane detection has been able to detect lanes accurately in complex scenarios, yet many fail to deliver real-time performance specifically with limited computational resources. In this work, we propose SwiftLane: a simple and light-weight, end-to-end deep learning based framework, coupled with the row-wise classification formulation for fast and efficient lane detection. This framework is supplemented with a false positive suppression algorithm and a curve fitting technique to further increase the accuracy. Our method achieves an inference speed of 411 frames per second, surpassing state-of the-art in terms of speed while achieving comparable results in terms of accuracy on the popular CULane benchmark dataset. In addition, our proposed framework together with TensorRT optimization facilitates real-time lane detection on a Nvidia Jetson AGX Xavier as an embedded system while achieving …

Dynamic adjustment of signal timing based on the number of pedestrians waiting at a crossing results in safer and more efficient intersections. Traditionally, such information is obtained through push-buttons or vision-based techniques. Though counting is possible with the latter, the techniques are associated with privacy concerns, are affected by poor lighting, and equipment is costly and bulky. We present a novel alternative that uses Wi-Fi Channel State Information (CSI) processed through a Deep Neural Network (DNN) model. The amplitude and phase of 51 Orthogonal Frequency Division Multiplexing sub carriers in the IEEE802.11n standard are captured with two ESP32 devices. Of the candidate DNNs trained with the CSI data, a ID-Convolutional Neural Network is experimentally demonstrated to count up to 12 pedestrians with an accuracy of 79 % at the current level of training. This can be generalized to …

Supporting parallel multi-priority data streams is vital for maintaining the quality of service (QoS) in vehicle-to-everything (V2X) communication. Hence, the European telecommunications standard institute (ETSI) has defined four packet types, with varying priority levels, to be used as broadcast packets in such communication. This paper studies the medium access control (MAC) layer performance of IEEE 802.11p and cellular-V2X (C-V2X) Mode 4 using discrete-time Markov chain (DTMC) based models, while considering parallel multi-priority data streams. The overall model consists of four queue models with their respective traffic generators, which are appropriately linked with the DTMCs modeling the MAC layer operations of IEEE 802.11p and C-V2X Mode 4. Closed-form solutions for the steady-state probabilities of the models are obtained, which are then utilized to derive expressions for key performance …

Vehicle-to-vehicle (V2V) communication plays a pivotal role in intelligent transport systems (ITS) with cellular-vehicle to everything (C-V2X) and IEEE 802.11p being the two competing enabling technologies. This paper presents multi-dimensional discrete-time Markov chain (DTMC) based models to study the medium access control (MAC) layer performance of the IEEE 802.11p standard and C-V2X Mode 4, considering periodic cooperative awareness messages (CAMs) and event-driven decentralized environmental notification messages (DENMs). Closed-form solutions for the steady-state probabilities of the models are obtained, which are then utilized to derive expressions for several key performance metrics. Numerical results are provided to draw insights on the performance. In particular, a performance comparison between IEEE 802.11p and C-V2X Mode 4 in terms of the average delay, the collision …

In this paper, a vision-based adaptive traffic light controller is proposed. The proposed controller was successfully deployed and tested as a complete system in a complex roundabout in Colombo city at a highly congested time. There were two main parts to this implementation. The first part was a vision-based traffic monitoring system. In this part, a system was developed so that it monitored lanes in a junction with cameras and extracted a traffic index based on traffic density, vehicle type, and pixel-wise velocity of vehicles by processing the video streams coming from cameras. The traffic signal light controlling part was the second part of the project. This part dealt with estimating a better timing adjustment for the existing system using a mathematical modeling approach while taking the extracted traffic index as input. This system was operated with the existing system with minimum alterations for easy real-world …

The enhanced distributed channel access (EDCA) mechanism enables IEEE 802.11p to accommodate differential quality of service (QoS) levels in vehicle-to-vehicle (V2V) communications, through four access categories (ACs). This paper presents multi-dimensional discrete-time Markov chain (DTMC) based model to study the effect of parallel operation of the ACs on the medium access control (MAC) layer performance of ITS-G5 IEEE 802.11p. The overall model consists of four queue models with their respective traffic generators, which are appropriately linked with the DTMCs modeling the operation of each AC. Closed-form solutions for the steady-state probabilities of the models are obtained, which are then utilized to derive expressions for key performance indicators at the MAC layer. An application for a highway scenario is presented to draw insights on the performance. The results show how the …

The response time of emergency vehicles (EVs) determines the outcome of many emergencies, thus improving the traversal time of EVs is of paramount importance. Vehicular communication is a key enabler of such an improvement. This paper studies two EV traversal algorithms, focusing mainly on their communication aspects. Fast moving dense traffic is modeled, and the traversal algorithms are implemented on top of the dedicated short-range communication (DSRC) / wireless access in vehicular environments (WAVE) protocol stack, while accounting for channel impairments such as path loss and fading. Algorithms that highlight the required packet transfers for the traversal and for safe lane changes are presented, and simulated in the VEINS framework for different traffic conditions. Simulation results show that the suitability of the EV traversal algorithms defer depending on the speed distribution of the …

Due to high costs at initiation, alternative communication strategies to dedicated short range communication (DSRC) have been looked at to facilitate quick deployment of intelligent transportation services. Wi-Fi Direct (WD), has come across as a candidate, and this paper focuses on the drawback of large transmission delays in WD. To this end, it studies the performance gains of using a broadcast mechanism on the downlink between the group owner (GO) and the clients of a WD group, instead of the currently used peer-to-peer method. Gains in terms of average total delay and the average energy consumption of the GO are presented using a theoretical analysis as well as a simulation study using OMNeT++. It is also shown that the degradation in performance on the downlink due to not having retransmissions is within tolerable limits given that the size of the group is selected properly.

We present a simulation study of a cooperate car following application implemented by the Wireless Access for Vehicular Environ-ments (WAVE) protocol stack, which uses the MAC and Physical lay-ers defined by the IEEE 802.11 p protocol. This is a simple Intelligent