A5022282223- Autonomous Vehicle Technology and Safety
- Video Surveillance and Tracking Methods
- Traffic Prediction and Management Techniques
- Anomaly Detection Techniques and Applications
- Human Pose and Action Recognition
- Robotics and Sensor-Based Localization
- Advanced Neural Network Applications
- Traffic and Road Safety
- Vehicle Dynamics and Control Systems
- Traffic control and management
- Remote Sensing and LiDAR Applications
Delft University of Technology
2019-2022
University of Amsterdam
2017-2018
Vrije Universiteit Amsterdam
2017
Next-generation automotive radars provide elevation data in addition to range-, azimuth- and Doppler velocity. In this experimental study, we apply a state-of-the-art object detector (PointPillars), previously used for LiDAR 3D data, such 3+1D radar (where 1D refers Doppler). ablation studies, first explore the benefits of additional information, together with that Doppler, cross section temporal accumulation, context multi-class road user detection. We subsequently compare detection...
Anticipating future situations from streaming sensor data is a key perception challenge for mobile robotics and automated vehicles. We address the problem of predicting path objects with multiple dynamic modes. The dynamics such targets can be described by Switching Linear Dynamical System (SLDS). However, predictions this probabilistic model cannot anticipate when change in mode will occur. propose to extract various types cues computer vision provide context on target's behavior,...
We learn motion models for cyclist path prediction on real-world tracks obtained from a moving vehicle, and propose to exploit the local road topology obtain better predictive distributions. The are extracted Tsinghua-Daimler Cyclist Benchmark detection, corrected vehicle egomotion. Tracks then spatially aligned curves crossings in road. study standard approach literature based Kalman Filters, as well mixture of specialized filters related specific orientations at junctions. Our experiments...
This paper proposes a Recurrent Neural Network (RNN) for cyclist path prediction to learn the effect of contextual cues on behavior directly in an end- to-end approach, removing need any annotations. The proposed RNN incorporates three distinct cues: one related actions cyclist, location road, and interaction between egovehicle. predicts Gaussian distribution over future position second into with higher accuracy, compared current state-of-the-art model that is based dynamic mode annotations,...
This paper presents our research platform Safe VRU for the interaction of self-driving vehicles with Vulnerable Road Users (VRUs, i.e., pedestrians and cyclists). The details design (implemented a modular structure within ROS) full stack vehicle localization, environment perception, motion planning, control, emphasis on perception planning modules. detects VRUs using stereo camera predicts their paths Dynamic Bayesian Networks (DBNs), which can account switching dynamics. planner is based...
This paper compares two models for context-based path prediction of objects with switching dynamics: a Dynamic Bayesian Network (DBN) and Recurrent Neural (RNN). These are instances larger model categories, distinguished by whether expert knowledge is explicitly crafted into the state representation (and thus interpretable) or learned from data, respectively. Both have shown state-of-the-art performance in previous work. In order to provide fair comparison, we ensure that both treated...
This paper presents an experimental study on 3D person localization (i.e. pedestrians, cyclists) in traffic scenes, using monocular vision and LiDAR data. We first analyze the detection performance of two top-ranking methods (PointPillars AVOD) KITTI benchmark, with respect to varying Intersection over Union (IoU) settings underlying parameters bounding box location, extent orientation. Given that dataset contains relatively few instances, we also consider new EuroCity Persons 2.5D (ECP2.5D)...
This thesis addresses the problem of path prediction for cyclists. Instead solely focusing on how to predict future trajectory based previous position measurements, this investigates leverage additional contextual information that can inform intent does with application intelligent vehicles in mind. That means all measurements come from point view a vehicle road. Additionally, resulting predictions must be usable by motion planner. In practice, are probability distribution over rather than...