Examensarbeten för masterexamen // Master Theses
Länka till denna samling:
Browse
Browsar Examensarbeten för masterexamen // Master Theses efter Program "Communication Engineering (MPCOM), MSc"
Visar 1 - 3 av 3
Sökresultat per sida
Sortera efter
- PostSemantic Segmentation in Marine Environment: Using 2D spherical projection and convolutional neural networks(2022) Dahlin, Emma; Jonsson, Hanna; Chalmers tekniska högskola / Institutionen för mekanik och maritima vetenskaper; Forsberg, Peter; Nordh, JonathanThe marine environment is constantly changing and therefore it can be difficult to control a vessel under these conditions. In this thesis, a method is proposed to interpret the surroundings to aid easy and safe travels on water. This is done through semantic segmentation by transforming 3D point clouds to 2D images, using a projection-based method. The transformation enables training with convolutional neural networks to achieve a fast and high performance network. The above method is successfully implemented in the marine environment and the results show that fewer classes are preferable to reach a high accuracy of the model. The features from the environment was unbalanced, which was compensated for by implementing a loss function that weighted the underrepresented classes higher. The model increased in performance for the minority classes. Furthermore, the real-time semantic segmentation was slower compared to the sensors update-time but there are possibilities to reduce the prediction time in future work. Precipitation was hard to detect due to low amounts of annotated data but the other surroundings could be detected in harsh weather conditions either way. The results show promising outcome for future implementation.
- PostStereo visual odometry using a supervised detector(2018) Li, Weiming; Jiang, Yumeng; Chalmers tekniska högskola / Institutionen för mekanik och maritima vetenskaper; Chalmers University of Technology / Department of Mechanics and Maritime SciencesStereo visual odometry, which is widely used in agent navigation because of its fast execution time and relatively good accuracy, is a process that computes the position and orientation of an agent using a stereo camera. Additionally, the method can build up a map which can be used for path planning. However, traditional stereo visual odometry only provides a content-less point cloud, making it difficult for path planning under some circumstances such as crossroads. To give content to the map, a convolutional neural network (CNN) classifier for detecting specific objects is created, and has been applied on the keypoints detected by oriented FAST and rotated BRIEF (ORB) detector. Thereafter, the labeled keypoints are inputted to a simplified keypoint-based visual odometry to build up the map. Our CNN classifier is trained on data provided by 2018 Chalmers formula student driveless (CFSD18) and achieved 98.97% accuracy in test data. Our stereo visual odometry algorithm is tested on an elliptic track and the mapping is compared to a raw GPS sensor data as ground truth. The average processing time of the whole approach is 68.6ms per frame with a CPU-based multi-threaded algorithm. Since our keypoint detector is a combination of ORB detector and CNN classifier, which is based on supervised learning, we have called it a supervised detector.
- PostTool development and quantitative analysis for naturalistic Left Turn Across Path/Opposite direction (LTAP/OD) driving scenarios(2016) Meng, Lin; Wang, Jifeng; Chalmers tekniska högskola / Institutionen för tillämpad mekanik; Chalmers University of Technology / Department of Applied MechanicsThis thesis aims to develop a tool to obtain key variables of other vehicles from video and apply this tool for the quantitative analysis of driver behaviour for Left Turn Across Path/Opposite Direction scenarios. The variables include relative speed and relative positions between subject vehicle and oncoming vehicle. Three methods are discussed and implemented in software tool for manual annotation,: a ground points method, a vehicle width method and an optical flow matching method In addition Kalman filter is applied to integrate this three methods together with a constant acceleration model. An experiment shows the range estimation result has an average percentage error of less than 10%, within the range 10m to 50m, and that the speed estimation has around a 10% error at approximately 10m and 20% error around 20m. Semi-automatic methods for extracting the desired variables is also presented. Based on manually selected tracking region in the first frame, and optical flow computed through the video, the desired (manually selected) region can be tracked. Optical flow vectors on the region has a relationship with motion. Motion estimation is accomplished with a matching process. After applying the tool on 102 LTAP/OD cases in a subset of EuroFOT data, the Post Encroachment Time was calculated for each. Results show that drivers feel comfortable to turn into the encroachment zone in a range between 2 and 4s after the last oncoming vehicle leaves that zone.