在不利的環境下做交通標誌的偵測與辨識是一件非常艱困的工作，無論在郊區或市區，複雜的環境、天候、陰影以及任何和光線有關的因素甚至是交通標誌遭到遮蔽都將使得偵測與辨識交通標誌變得相當困難。在本篇論文中，我們定義出較寬鬆的顏色分類(color thresholding)方法，配合一些交通標誌的特徵(如外形)來實作出召回率(Recall)較高的偵測系統，另外在辨識方面，最重要的是找出好的辨識特徵，因此我們利用離散餘弦轉換(discrete cosine transform)和奇異值分解(singular value decomposition)處理待辨識標誌擷取其特徵，並配合一些其他的交通標誌特徵，當作類神經網路(ANN)、naïve Bayes classifier等辨識方法的輸入，來幫助我們完成辨識的工作。目前實作出來的系統在有挑戰性的測試資料下有七成六左右的辨識率。 / Robust traffic sign recognition can be a difficult task if we aim at detecting and recognizing traffic signs in images captured under unfavorable environments. Complex background, weather, shadow, and other illumination-related problems may make it difficult to detect and recognize signs in the rural as well as the urban areas. In this thesis, I define a formula for color classification and apply other related features such as the shape of the traffic signs to implement the detection component that offers high recall rate. In traffic sign recognition, the most important thing is to get the effective features. I use discrete cosine transform and singular value decomposition to collect the invariant features of traffic signs that will not be severely interfered by disturbing environments. These invariant features can be used as the input to artificial neural networks or naïve Bayes models to achieve the recognition task. This system yields satisfactory performance about 76% recognition rate when I test them with very challenging data.

Autonomous driving is increasingly popular among people and automotive industries in realizing their presence both in passenger and goods transportation. Safer autonomous navigation might be very challenging if there is a failure in sensing system. Among several sensing systems, image classification plays a major role in understanding the road signs and to regulate the vehicle control based on urban road rules. Hence, a robust classifier algorithm irrespective of camera position, view angles, environmental condition, different vehicle size & type (Car, Bus, Truck, etc.,) of an autonomous platform is of prime importance. In this study, Convolutional Neural Network (CNN) based classifier algorithm has been implemented to ensure improved robustness for recognizing traffic signs. As training data play a crucial role in supervised learning algorithms, there come an effective dataset requirement which can handle dynamic environmental conditions and other variations caused due to the vehicle motion (will be referred as challenges). Since the collected training data might not contain all the dynamic variations, the model weakness can be identified by exposing it to variations (Blur, Darkness, Shadow, etc.,) faced by the vehicles in real-time as a initial testing sequence. To overcome the weakness caused due to the training data itself, an effective augmentation technique enriching the training data in order to increase the model capacity for withstanding the variations prevalent in urban environment has been proposed. As a major contribution, a framework has been developed to identify model weakness and successively introduce a targeted augmentation methodology for classification improvement. Targeted augmentation is based on estimated weakness caused due to the challenges with difficulty levels, only those necessary for better classification were then augmented further. Predictive Augmentation (PA) and Predictive Multiple Augmentation (PMA) are the two proposed methods to adapt the model based on targeted challenges by delivering with high numerical value of confidence. We validated our framework on two different training datasets (German Traffic Sign Recognition Benchmark (GTSRB) and Heavy Vehicle data collected from bus) and with 5 generated test groups containing varying levels of challenge (simple to extreme). The results show impressive improvement by ≈ 5-20% in overall classification accuracy thereby keeping their high confidence.

In this thesis, detection of traffic signs is studied. Since, both color and shape properties of traffic signs are distinctive / these two properties have been employed for detection. Detection using color properties is studied in two different color domains in order to examine and compare the advantages and the disadvantages of these domains for detection purposes. In addition to their color information, shape information is also employed for detection purpose. Edge information (obtained by using the Sobel Operator) of the images/frames is considered as search domain to find triangular, rectangular, octagonal and circular traffic signs. In order to improve the performance of detection process a joint implementation of shape and color based algorithms is utilized. Two different methods have been used v in order to combine these two features. Both of the algorithms help reducing the number of pixels to check whether they belong to a sign or not. This, of course, reduces the processing time of detection process. Each utilized algorithm is tested and compared with the others by using both static images from different sources and video streams. Images having adverse properties are used in order to state algorithms response for some specific conditions such as bad illumination and shadow. After implementation, results show that joint implementation of the color and shape based detection algorithms produces more accurate results. Moreover, joint implementation reduces the processing time of the detection process when compared to application of algorithms individually since it diminishes the search domain.

O uso de sistemas de assistência ao motorista (DAS) baseados em visão tem contribuído consideravelmente na redução de acidentes e consequentemente no auxílio de uma melhor condução. Estes sistemas utilizam basicamente uma câmera de vídeo embarcada (normalmente fixada no para-brisa) com o propósito de extrair informações acerca da rodovia e ajudar o condutor num melhor processo de dirigibilidade. Pequenas distrações ou a perda de concentração podem ser suficientes para que um acidente ocorra. Este trabalho apresenta uma proposta para o desenvolvimento de algoritmos para extrair informações sobre a sinalização em rodovias. Mais precisamente, serão abordados algoritmos de calibração de câmera explorando a geometria da pista, de extração da marcação de pintura (sinalização horizontal) e detecção e identificação de placas de trânsito (sinalização vertical). Os resultados experimentais indicam que o método de calibração de câmera alcançou bons resultados na obtenção dos parâmetros extrínsecos com erros inferiores a 0:5 . O erro médio encontrado nos experimentos com relação a estimativa da altura da câmera foi em torno de 12 cm (erro relativo aproximado de 10%), permitindo explorar o uso da realidade aumentada como uma possível aplicação. A acurácia global para a detecção e reconhecimento da sinalização horizontal (marcas seccionadas, contínuas e mistas) foi acima de 96% perante uma diversidade de situações apresentadas, tais como: sombras, variação de iluminação, degradação do asfalto e pintura. O uso da câmera calibrada para a detecção da sinalização vertical contribui para delimitar o espaço de varredura da janela deslizante do detector, bem como realizar a procura por placas em uma única escala para cada região de busca, caracterizada pela distância ao veículo. Os resultados apresentados reportam uma taxa global de classificação de aproximadamente 99% para o sinal de proibido ultrapassar, considerando-se uma base de dados limitada a 962 amostras. / The use of driver assistance systems (DAS) based on computer vision has helped considerably in reducing accidents and consequently aid in better driving. These systems primarily use an embedded video camera (usually fixed on the windshield) for the purpose of extracting information about the highway and assisting the driver in a better handling process. Small distractions or loss of concentration may be sufficient for an accident to occur. This work presents the development of algorithms to extract information about traffic signs on highways. More specifically, this work will tackle a camera calibration algorithm that exploits the geometry of the road track, algorithms for the extraction of road marking paint (lane markings) and detection and identification of vertical traffic signs. Experimental results indicate that the proposed method for obtaining the extrinsic parameters achieve good results with errors of less than 0:5 . The average error in our experiments, related to the camera height, were around 12 cm (relative error around 10%). Global accuracy for the detection and classification of road lane markings (dashed, solid, dashed-solid, solid-dashed or double solid) were over 96%. Finally, our camera calibration algorithm was used to reduce the search region and to define the scale of a slidingwindow detector for vertical traffic signs. The use of the calibrated camera for the detection of traffic signs contributes to define the scanning area of the sliding window and perform a search for signs on a unique scale for each region of interest, determined by the distance to the vehicle. The results reported a global classification rate of approximately 99% for the no overtaking sign, considering a limited of 962 samples.

O uso de sistemas de assistência ao motorista (DAS) baseados em visão tem contribuído consideravelmente na redução de acidentes e consequentemente no auxílio de uma melhor condução. Estes sistemas utilizam basicamente uma câmera de vídeo embarcada (normalmente fixada no para-brisa) com o propósito de extrair informações acerca da rodovia e ajudar o condutor num melhor processo de dirigibilidade. Pequenas distrações ou a perda de concentração podem ser suficientes para que um acidente ocorra. Este trabalho apresenta uma proposta para o desenvolvimento de algoritmos para extrair informações sobre a sinalização em rodovias. Mais precisamente, serão abordados algoritmos de calibração de câmera explorando a geometria da pista, de extração da marcação de pintura (sinalização horizontal) e detecção e identificação de placas de trânsito (sinalização vertical). Os resultados experimentais indicam que o método de calibração de câmera alcançou bons resultados na obtenção dos parâmetros extrínsecos com erros inferiores a 0:5 . O erro médio encontrado nos experimentos com relação a estimativa da altura da câmera foi em torno de 12 cm (erro relativo aproximado de 10%), permitindo explorar o uso da realidade aumentada como uma possível aplicação. A acurácia global para a detecção e reconhecimento da sinalização horizontal (marcas seccionadas, contínuas e mistas) foi acima de 96% perante uma diversidade de situações apresentadas, tais como: sombras, variação de iluminação, degradação do asfalto e pintura. O uso da câmera calibrada para a detecção da sinalização vertical contribui para delimitar o espaço de varredura da janela deslizante do detector, bem como realizar a procura por placas em uma única escala para cada região de busca, caracterizada pela distância ao veículo. Os resultados apresentados reportam uma taxa global de classificação de aproximadamente 99% para o sinal de proibido ultrapassar, considerando-se uma base de dados limitada a 962 amostras. / The use of driver assistance systems (DAS) based on computer vision has helped considerably in reducing accidents and consequently aid in better driving. These systems primarily use an embedded video camera (usually fixed on the windshield) for the purpose of extracting information about the highway and assisting the driver in a better handling process. Small distractions or loss of concentration may be sufficient for an accident to occur. This work presents the development of algorithms to extract information about traffic signs on highways. More specifically, this work will tackle a camera calibration algorithm that exploits the geometry of the road track, algorithms for the extraction of road marking paint (lane markings) and detection and identification of vertical traffic signs. Experimental results indicate that the proposed method for obtaining the extrinsic parameters achieve good results with errors of less than 0:5 . The average error in our experiments, related to the camera height, were around 12 cm (relative error around 10%). Global accuracy for the detection and classification of road lane markings (dashed, solid, dashed-solid, solid-dashed or double solid) were over 96%. Finally, our camera calibration algorithm was used to reduce the search region and to define the scale of a slidingwindow detector for vertical traffic signs. The use of the calibrated camera for the detection of traffic signs contributes to define the scanning area of the sliding window and perform a search for signs on a unique scale for each region of interest, determined by the distance to the vehicle. The results reported a global classification rate of approximately 99% for the no overtaking sign, considering a limited of 962 samples.

O uso de sistemas de assistência ao motorista (DAS) baseados em visão tem contribuído consideravelmente na redução de acidentes e consequentemente no auxílio de uma melhor condução. Estes sistemas utilizam basicamente uma câmera de vídeo embarcada (normalmente fixada no para-brisa) com o propósito de extrair informações acerca da rodovia e ajudar o condutor num melhor processo de dirigibilidade. Pequenas distrações ou a perda de concentração podem ser suficientes para que um acidente ocorra. Este trabalho apresenta uma proposta para o desenvolvimento de algoritmos para extrair informações sobre a sinalização em rodovias. Mais precisamente, serão abordados algoritmos de calibração de câmera explorando a geometria da pista, de extração da marcação de pintura (sinalização horizontal) e detecção e identificação de placas de trânsito (sinalização vertical). Os resultados experimentais indicam que o método de calibração de câmera alcançou bons resultados na obtenção dos parâmetros extrínsecos com erros inferiores a 0:5 . O erro médio encontrado nos experimentos com relação a estimativa da altura da câmera foi em torno de 12 cm (erro relativo aproximado de 10%), permitindo explorar o uso da realidade aumentada como uma possível aplicação. A acurácia global para a detecção e reconhecimento da sinalização horizontal (marcas seccionadas, contínuas e mistas) foi acima de 96% perante uma diversidade de situações apresentadas, tais como: sombras, variação de iluminação, degradação do asfalto e pintura. O uso da câmera calibrada para a detecção da sinalização vertical contribui para delimitar o espaço de varredura da janela deslizante do detector, bem como realizar a procura por placas em uma única escala para cada região de busca, caracterizada pela distância ao veículo. Os resultados apresentados reportam uma taxa global de classificação de aproximadamente 99% para o sinal de proibido ultrapassar, considerando-se uma base de dados limitada a 962 amostras. / The use of driver assistance systems (DAS) based on computer vision has helped considerably in reducing accidents and consequently aid in better driving. These systems primarily use an embedded video camera (usually fixed on the windshield) for the purpose of extracting information about the highway and assisting the driver in a better handling process. Small distractions or loss of concentration may be sufficient for an accident to occur. This work presents the development of algorithms to extract information about traffic signs on highways. More specifically, this work will tackle a camera calibration algorithm that exploits the geometry of the road track, algorithms for the extraction of road marking paint (lane markings) and detection and identification of vertical traffic signs. Experimental results indicate that the proposed method for obtaining the extrinsic parameters achieve good results with errors of less than 0:5 . The average error in our experiments, related to the camera height, were around 12 cm (relative error around 10%). Global accuracy for the detection and classification of road lane markings (dashed, solid, dashed-solid, solid-dashed or double solid) were over 96%. Finally, our camera calibration algorithm was used to reduce the search region and to define the scale of a slidingwindow detector for vertical traffic signs. The use of the calibrated camera for the detection of traffic signs contributes to define the scanning area of the sliding window and perform a search for signs on a unique scale for each region of interest, determined by the distance to the vehicle. The results reported a global classification rate of approximately 99% for the no overtaking sign, considering a limited of 962 samples.

This paper proposes robust algorithm for detection of traffic signs in well light conditional. The algorithm uses colour based segmentation method for finding red traffic signs. Fast radial symmetry method FRS is used for identification of constituent shapes. Traffic signs are divided into four classes on the basis of the method.

No description available.

In recent years, AI has developed significantly and become more popular than ever before. The applications of AI are expanding, making knowledge about its application and the systems it can be applied to more important. This project compares and evaluates deep learning models for object detection of traffic signs on the embedded systems Nvidia Jetson Nano and Raspberry Pi 3 Model B. The project compares and evaluates the models YOLOv5, SSD Mobilenet V1, FOMO, and Efficientdet-lite0. The project evaluates the performance of these models on the aforementioned embedded systems, measuring metrics such as CPU usage, FPS and RAM. Deep learning models are resource-intensive, and embedded systems have limited resources. Embedded systems often have different types of processor architectures than regular computers, which means that some frameworks and libraries may not be compatible. The results show that the tested systems are capable of object detection but with varying performance. Jetson Nano performs at a level we consider sufficiently high for use in production depending on the specific requirements. Raspberry Pi 3 performs at a level that may not be acceptable for real-time recognition of traffic signs. We see the greatest potential for Efficientdet-lite0 and YOLOv5 in recognizing traffic signs. The distance at which the models detect signs seems to be important for how many signs they find. For this reason, SSD MobileNet V1 is not recommended without further trai-ning despite its superior speed. YOLOv5 stood out as the model that detected signs at the longest distance and made the most detections overall. When considering all the results, we believe that Efficientdet-lite0 is the model that performs the best. / Under de senaste åren har AI utvecklats mycket och blivit mer populärt än någonsin. Tillämpningsområdena för AI ökar och därmed blir kunskap om hur det kan tillämpas och på vilka system viktigare. I det här projektet jämförs och utvärderas djupinlärningsmodeller för objektdetektering av trafikskyltar på de inbyggda systemen Nvidia Jetson Nano och Raspberry Pi 3 Model B. Modellerna som jämförs och utvärderas är YOLOv5, SSD Mobilenet V1, FOMO och Efficientdet-lite0. För varje modell mäts blandannat CPU-användning, FPS och RAM. Modeller för djupinlärning är resurskrävande och inbyggda system har begränsat med resurser. Inbyggda system har ofta andra typer av processorarkitekturer än en vanlig dator vilket gör att olika ramverk och andra bibliotek inte är kompatibla. Resultaten visar att de testade systemen klarar av objektdetektering med varierande prestation. Jetson Nano presterar på en nivå vi anser vara tillräckligt hög för användning i produktion beroende på hur hårda krav som ställs. Raspberry Pi 3 presterar på en nivå som möjligtvis inte är acceptabel för igenkänning av trafikskyltar i realtid. Vi ser störst potential för Efficientdet-lite0 och YOLOv5 för igenkänning av trafikskyltar. Hur långt avstånd modellerna upptäcker skyltar på verkar vara viktigt för hur många skyltar de hittar. Av den anledningen är SSD MobileNet V1 inte att rekommendera utan vidare träning trots sin överlägsna hastighet. YOLOv5 utmärkte sig som den som upptäckte skyltar på längst avstånd och som gjorde flest upptäckter totalt. När alla resultat vägs in anser vi dock att Efficientdet-lite0 är den modell som presterar bäst.

The thesis with the title “Designing and simulating a Car2X communication system using the example of an intelligent traffic sign” has been done in Chemnitz University of Technology in the faculty of Computer Science. The purpose of this thesis is to define a layered architecture for Infrastructure to Vehicle (I2V) communication and the implementation of a sample intelligent traffic sign (variable speed limit) application for a Car2X communication system. The layered architecture of this thesis is defined based on three related projects. The application is implemented using the defined layered architecture. Considering the availability of hardware, the implementation is done using the network simulator OMNET++. To check the feasibility of the application three scenarios are created and integrated with the application. The evaluation is done based on the result log files of the simulation which show that the achieved results conform with the expected results, except some minor limitations.