No description available.

The World Health Organization predicts that by the year 2030, road traffic injuries will be one of the top five leading causes of death. Many of these deaths and injuries can be prevented by driving cars properly equipped with state-of-the-art safety and driver assistance systems. Some examples are auto-brake and auto-collision avoidance which are becoming more and more popular on the market today. A recent study by a Swedish insurance company has shown that on roadswith speeds up to 50 km/h an auto-brake system can reduce personal injuries by up to 64 percent. In fact in an estimated 40 percent of crashes, the auto-brake reduced the effects to the degree that no personal injury was sustained. It is imperative that these so called Advanced Driver Assistance Systems, to be really effective, have good situational awareness. It is important that they have adequate information of the vehicle’s immediate surroundings. Where are other cars, pedestrians or motorcycles relative to our own vehicle? How fast are they driving and in which lane? How is our own vehicle driving? Are there objects in the way of our own vehicle’s intended path? These and many more questions can be answered by a properly designed system for situational awareness. In this thesis we design and evaluate, both quantitatively and qualitatively, sensor fusion algorithms for multi-target tracking. We use a combination of camera and radar information to perform fusion and find relevant objects in a cluttered environment. The combination of these two sensors is very interesting because of their complementary attributes. The radar system has high range resolution but poor bearing resolution. The camera system on the other hand has a very high bearing resolution. This is very promising, with the potential to substantially increase the accuracy of the tracking system compared to just using one of the two. We have also designed algorithms for path prediction and a first threat awareness logic which are both qualitively evaluated.

In modern cars, advanced driver assistance systems are used to aid the driver and increase the automobile safety. An example of such a system is the night vision system designed to detect and warn for pedestrians in danger of being hit by the car. To determine if a warning should be given when a pedestrian is detected, the system requires a prediction of the future path of the car for up to four seconds ahead in time. In this master's thesis, a new path prediction algorithm based on satellite positioning and a digital map database has been developed. The algorithm uses an extended Kalman filter to get an accurate estimate of the current position and heading direction of the car. The estimate is then matched to a position in the map database and the possible future paths of the vehicle are predicted using the road network. The performance of the path prediction algorithm has been evaluated on recorded night vision sequences corresponding to 15 hours of driving. The results show that map-based path prediction algorithms are superior to dead-reckoning methods for longer time horizons. It has also been investigated whether vision-based lane detection and tracking can be used to improve the path prediction. A prediction method using lane markings has been implemented and evaluated on recorded sequences. Based on the results, the conclusion is that lane detection can be used to support a path prediction system when lane markings are clearly visible.

No description available.

Due to automation, the world is changing at a rapid pace. Autonomous agents have become more common over the last several years and, as a result, have created a need for improved software to back them up. The most important aspect of this greater software is path prediction, as robots need to be able to decide where to move in the future. In order to accomplish this, a robot must know how to avoid humans, putting frame prediction at the core of many modern day solutions. A popular way to solve this complex problem of frame prediction is Auto Encoder LSTMs. Though there are many implementations of this, at its core, it is a neural network comprised of a series of time sensitive processing blocks that shrink and then grow the data’s dimensions to make a prediction. The idea of using Auto Encoder styled networks to do frame prediction has also been adapted by others to make Temporal Encoders. These neural networks work much like traditional Auto Encoders, in which the data is reduced then expanded back up. These networks attempt to tease out a series of frames, including a predictive frame of the future. The problem with many of these networks is that they take an immense amount of computation power, and time to get them performing at an acceptable level. This thesis presents possible ways of pre-processing input frames to these networks in order to gain performance, in the best case seeing a 360x improvement in accuracy compared to the original models. This thesis also extends the work done with Temporal Encoders to create more precise prediction models, which showed consistent improvements of at least 50% for some metrics. All of the generated models were compared using a simulated data set collected from recordings of ground level viewpoints from Cities: Skylines. These predicted frames were then analyzed using a common perceptual distance metric, that is, Minkowski distance, as well as a custom metric that tracked distinct areas in frames. All of the following was run on a constrained system in order to see the effects of the changes as they pertain to systems with limited hardware access.