In this paper we present a time-efficient estimation framework for camera-based pedestrian tracking from a moving host car using a monocular camera. An image processing system processes the camera output to find the location of objects of interest in each frame. The position and sensor information about the host translation and rotation are passed to a tracking module. The module uses the position of the detected object's foot point as measurement input and connects them over time to estimate the movement of the objects of interest in order to reduce noise and single frame failures in the detection process. We have developed a new method to estimate the target movement which takes into account the host movement and allows to exploit prior information about the intrinsic and extrinsic camera parameters. The basic idea is to assume that host and target movements can be modelled as 2-dimensional movements on a flat ground-plane. Our developed motion model is based on this assumption and includes host motion as well as the target ego motion. A measurement is modelled as a perspective projection of a point on the groundplane to the image plane. The motion and the measurement model are combined by an Unscented Kalman filter. This filter is relatively new and has not been applied for pedestrian tracking before. Finally, we present a new logical initialization strategy for the selected filter, a part that is left out by most other publications. First results indicate that our approach gives good tracking results and allows to track pedestrians from a moving host in real time.

Nowadays, the camera online calibration module has been a fundamental and often requested component in an Advanced Driver Assistance System (ADAS). The proposed system provides an efficient and practical solution to such request, and also shows technical advances compared to earlier systems. It utilizes the lane markings for camera orientation calibration. At each image frame, multiple vanishing points of the lane markings are estimated using the weighted least squares method, followed by a tracking process with Kalman Filter for better consistency and robustness. With the filtered vanishing point the camera extrinsic tilt and pan angles can be estimated. Even though the proposed system relies on the lane markings for calibration, unlike other similar systems, the number of the lane markings in the system is not restricted, and the shape of the lane markings is also not restricted to straight lines or any other pre-defined models. A Monte Carlo evaluation scheme is devised for that purpose using real world driving sequences. The final result has shown that given an initial calibration error, in ±4 degree interval w.r.t. ground truth for both tilt and pan angles, the proposed system is capable of converging to accurate angles and providing consistent results.

This paper presents two new real-time approaches to segmentation of TV news shows into topics. The goal of this research work is the high precision retrieval of topics from TV news. For that purpose, the detection of correct topic boundaries is of great importance. We introduce a stochastic and a rule-based topic model based on HMMs. The former combines features from the visual as well as from the audio channel of the news show, whereas the latter uses the video channel only. They are compared to the detection of topics using only the audio channel, which is common for many other approaches. The paper contains the following innovations: 1) The detected segment boundaries correspond directly to topics and not to video or audio cuts, as most other segmentation methods. 2) An advanced stochastic topic model is introduced that uses audio as well as video features.3) The introduced HMM-based approaches both outperform the audio-based approach. One algorithm has a very good topic boundary detection rate, whereas the other minimizes the number of wrongly inserted boundaries without missing too many real boundaries.

No abstract

No abstract

No abstract

No abstract

No abstract