Vehicle detection is important for advanced driver assistance systems (ADAS). Both LiDAR and cameras are often used. LiDAR provides excellent range information but with limits to object identification; on the other hand, the camera allows for better recognition but with limits to the high resolution range information. This paper presents a sensor fusion based vehicle detection approach by fusing information from both LiDAR and cameras. The proposed approach is based on two components: a hypothesis generation phase to generate positions that potential represent vehicles and a hypothesis verification phase to classify the corresponding objects. Hypothesis generation is achieved using the stereo camera while verification is achieved using the LiDAR. The main contribution is that the complementary advantages of two sensors are utilized, with the goal of vehicle detection. The proposed approach leads to an enhanced detection performance; in addition, maintains tolerable false alarm rates compared to vision based classifiers. Experimental results suggest a performance which is broadly comparable to the current state of the art, albeit with reduced false alarm rate.
This paper deals with recognizing human actions in depth video data. Current state-of-the-art action recognition methods use hand-designed features, which are difficult to produce and time-consuming to extend to new modalities. In this paper, we propose a novel, 3.5D representation of a depth video for action recognition. A 3.5D graph of the depth video consists of a set of nodes that are the joints of the human body. Each joint is represented by a set of spatio-temporal features, which are computed by an unsupervised learning approach. However, if occlusions occur, the 3D positions of the joints are noisy which increases the intra-class variations in action classes. To address this problem, we propose the Ensemble Weighted Multi-Instance Learning approach (EnwMi) for the action recognition task. It considers the class imbalance and intra-class variations. We formulate the action recognition task with depth videos as a weighted multi-instance problem. We further integrate an ensemble learning method into the weighted multi-instance learning framework. Our approach is evaluated on Microsoft Research Action3D dataset, and the results show that it outperforms state-of-the-art methods.
Highly assisted and Autonomous Driving is dependent on the accurate localization of both the vehicle and other targets within the environment. With increasing traffic on roads and wider proliferation of low cost sensors, a vehicle-infrastructure cooperative localization scenario can provide improved performance over traditional mono-platform localization. The paper highlights the various challenges in the process and proposes a solution based on Factor Graphs which utilizes the concept of topology of vehicles. A Factor Graph represents probabilistic graphical model as a bipartite graph. It is used to add the inter-vehicle distance as constraints while localizing the vehicle. The proposed solution is easily scalable for many vehicles without increasing the execution complexity. Finally simulation indicates that incorporating the topology information as a state estimate can improve performance over the traditional Kalman Filter approach.
In this paper we investigate the feasibility for using a Synthetic Aperture Radar (SAR) to detect radar scatterers in support of advanced driver assistance systems. Specifically, we consider the detection of radar scatterers physically embedded into lane and carriageway boundaries similar to way optical retroreflectors (cats eyes) are used in present infrastructure. We use simulations to generate high resolution SAR images for detecting and localizing radar scatterers. The simulated results presented here highlight the feasibility of the technique and provide a platform for further investigation. This paper facilitates the realization of the role of modified infrastructure for improving the sensing capability of highly assisted and autonomous vehicles.