With the rapid improvement of the Advanced Driver Assistant System (ADAS), autonomous driving has become one of the most common hot topics in recent years. While driving, many technologies related to autonomous driving choose to use the sensors installed on the vehicle to collect the information of road status and the environment outside. This aims to warn the driver to perceive the potential danger in the fastest time, which has become the focus of autonomous driving in recent years. Although autonomous driving brings plenty of conveniences to people, the safety of it is still facing difficulties. During driving, even the experienced driver can not guarantee focus on the status of the road all the time. Thus, lane departure warning system (LDWS) becomes developed. The purpose of LDWS is to determine whether the vehicle is in the safe driving area. If the vehicle is out of this area, LDWS will detect it and alert the driver by the sensors, such as sound and vibration, in order to make the driver back to the safe driving area. This thesis proposes a novel lightweight LDWS model LEHA, which divides the entire LDWS into three stages: image preprocessing, lane detection, and lane departure recognition. Different from the deep learning methods of LDWS, our LDWS model LEHA can achieve high accuracy and efficiency by relying only on simple hardware. The image preprocessing stage aims to process the original road image to remove the noise which is irrelevant to the detection result. In this stage, we apply a novel algorithm of grayscale preprocessing to convert the road image to a grayscale image, which removes the color of it. Then, we design a binarization method to greatly extract the lane lines from the background. A newly-designed image smoothing is added to this stage to reduce most of the noise, which improves the accuracy of the following lane detection stage. After obtaining the processed image, the lane detection stage is applied to detect and mark the lane lines. We use region of interest (ROI) to remove the irrelevant parts of the road image to reduce the detection time. After that, we introduce the Canny edge detection method, which aims to extract the edges of the lane lines. The last step of LDWS in the lane detection stage is a novel Hough transform method, the purpose of it is to detect the position of the lane and mark it. Finally, the lane departure recognition stage is used to calculate the deviation distance between the vehicle and the centerline of the lane to determine whether the warning needs to turn on. In the last part of this paper, we present the experiment results which show the comparison results of different lane conditions. We do the statistic of the proposed LDWS accuracy in terms of detection and departure. The detection rate of our proposed LDWS is 98.2% and the departure rate of it is 99.1%. The average processing time of our proposed LDWS is 20.01 x 10⁻³s per image.

Driving is one of the most common and preferred forms of transport used in our actual society. However, according to studies, it is also one of the most dangerous. One solution to increase safety on the road is applying technology to automate and prevent avoidable human errors. Nevertheless, despite the efforts to obtain reliable systems, we have yet to find a reliable and safe enough solution for solving autonomous driving. One of the reasons is that many drives are done in conditions far from the ideal, with variable lighting conditions and fast-paced, unpredictable environments. This project develops and evaluates an algorithm that takes the input of dynamic vision sensors (DVS) and runs on neuromorphic spiking neural networks (SNN) to obtain a robust road lane tracking system. We present quantitative and qualitative metrics that evaluate the performance of lane recognition in low light conditions against conventional algorithms. This project is motivated by the main advantages of neuromorphic vision sensors: recognizing a high dynamic range and allowing a high-speed image capture. Another improvement of this system is the computational speed and power efficiency that characterize neuromorphic hardware based on spiking neural networks. The results obtained show a similar accuracy of this new algorithm compared to previous implementations on conventional hardware platforms. Most importantly, it accomplishes the proposed task with lower latency and computing power requirements than previous algorithms. / Att köra bil är ett av de vanligaste och mest populära transportsätten i vårt samhälle. Enligt forskningen är det också ett av de farligaste. En lösning för att öka säkerheten på vägarna är att med teknikens hjälp automatisera bilkörningen och på så sätt förebygga misstag som beror på den mänskliga faktorn. Trots ansträngningarna för att få fram tillförlitliga system har man dock ännu inte hittat en tillräckligt tillförlitlig och säker lösning för självkörande bilar. En av orsakerna till det är att många körningar sker under förhållanden som är långt ifrån idealiska, med varierande ljusförhållanden och oförutsägbara miljöer i höga hastigheter. I det här projektet utvecklar och utvärderar vi en algoritm som tar emot indata från dynamiska synsensorer (Dynamic Vision Sensors, DVS) och kör datan på neuromorfiska pulserande neuronnät (Spiking Neural Networks, SNN) för att skapa ett robust system för att läsa av vägbanan. Vi presenterar en kvantitativ och kvalitativ utvärdering av hur väl systemet läser av körbanans linjer i svagt ljus, och jämför därefter resultaten med dem för tidigare algoritmer. Detta projekt motiveras av de viktigaste fördelarna med neuromorfiska synsensorer: brett dynamiskt omfång och hög bildtagningshastighet. En annan fördel hos detta system är den korta beräkningstiden och den energieffektivitet som kännetecknar neuromorfisk hårdvara baserad på pulserande neuronnät. De resultat som erhållits visar att den nya algoritmen har en liknande noggrannhet som tidigare algoritmer på traditionella hårdvaruplattformar. I jämförelse med den traditionella tekniken, utför algoritmen i den föreliggande studien sin uppgift med kortare latenstid och lägre krav på processorkraft. / La conducción es una de las formas de transporte más comunes y preferidas en la actualidad. Sin embargo, diferentes estudios muestran que también es una de las más peligrosas. Una solución para aumentar la seguridad en la carretera es aplicar la tecnología para automatizar y prevenir los evitables errores humanos. No obstante, a pesar de los esfuerzos por conseguir sistemas fiables, todavía no hemos encontrado una solución suficientemente fiable y segura para resolver este reto. Una de las razones es el entorno de la conducción, en situaciones que distan mucho de las ideales, con condiciones de iluminación variables y entornos rápidos e imprevisibles. Este proyecto desarrolla y evalúa un algoritmo que toma la entrada de sensores de visión dinámicos (DVS) y ejecuta su computación en redes neuronales neuromórficas (SNN) para obtener un sistema robusto de seguimiento de carriles en carretera. Presentamos métricas cuantitativas y cualitativas que evalúan el rendimiento del reconocimiento de carriles en condiciones de poca luz, frente a algoritmos convencionales. Este proyecto está motivado por la validación de las ventajas de los sensores de visión neuromórficos: el reconocimiento de un alto rango dinámico y la captura de imágenes de alta velocidad. Otra de las mejoras que se espera de este sistema es la velocidad de procesamiento y la eficiencia energética que caracterizan al hardware neuromórfico basado en redes neuronales de impulsos. Los resultados obtenidos muestran una precisión similar entre el nuevo algoritmo en comparación con implementaciones anteriores en plataformas convencionales. Y lo que es más importante, realiza la tarea propuesta con menor latencia y requisitos de potencia de cálculo.