Efficient Transformer-based 3D Object Detection with Dynamic Token Halting

no code implementations • 9 Mar 2023 • Mao Ye, Gregory P. Meyer, Yuning Chai, Qiang Liu

Although halting a token is a non-differentiable operation, our method allows for differentiable end-to-end learning by leveraging an equivalent differentiable forward-pass.

3D Object Detection Autonomous Vehicles +1

MultiXNet: Multiclass Multistage Multimodal Motion Prediction

no code implementations • 3 Jun 2020 • Nemanja Djuric, Henggang Cui, Zhaoen Su, Shangxuan Wu, Huahua Wang, Fang-Chieh Chou, Luisa San Martin, Song Feng, Rui Hu, Yang Xu, Alyssa Dayan, Sidney Zhang, Brian C. Becker, Gregory P. Meyer, Carlos Vallespi-Gonzalez, Carl K. Wellington

One of the critical pieces of the self-driving puzzle is understanding the surroundings of a self-driving vehicle (SDV) and predicting how these surroundings will change in the near future.

motion prediction

RV-FuseNet: Range View Based Fusion of Time-Series LiDAR Data for Joint 3D Object Detection and Motion Forecasting

no code implementations • 21 May 2020 • Ankit Laddha, Shivam Gautam, Gregory P. Meyer, Carlos Vallespi-Gonzalez, Carl K. Wellington

We show that our approach significantly improves motion forecasting performance over the existing state-of-the-art.

3D Object Detection Motion Forecasting +4

LaserFlow: Efficient and Probabilistic Object Detection and Motion Forecasting

no code implementations • 12 Mar 2020 • Gregory P. Meyer, Jake Charland, Shreyash Pandey, Ankit Laddha, Shivam Gautam, Carlos Vallespi-Gonzalez, Carl K. Wellington

In this work, we present LaserFlow, an efficient method for 3D object detection and motion forecasting from LiDAR.

3D Object Detection Motion Forecasting +1

SDVTracker: Real-Time Multi-Sensor Association and Tracking for Self-Driving Vehicles

no code implementations • 9 Mar 2020 • Shivam Gautam, Gregory P. Meyer, Carlos Vallespi-Gonzalez, Brian C. Becker

Accurate motion state estimation of Vulnerable Road Users (VRUs), is a critical requirement for autonomous vehicles that navigate in urban environments.

Association Autonomous Vehicles +2

An Alternative Probabilistic Interpretation of the Huber Loss

no code implementations • CVPR 2021 • Gregory P. Meyer

As a result, our interpretation provides an intuitive way to identify well-suited hyper-parameters by approximating the amount of noise in the data, which we demonstrate through a case study and experimentation on the Faster R-CNN and RetinaNet object detectors.

Learning an Uncertainty-Aware Object Detector for Autonomous Driving

1 code implementation • 24 Oct 2019 • Gregory P. Meyer, Niranjan Thakurdesai

The capability to detect objects is a core part of autonomous driving.

Autonomous Driving object-detection +1

Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation

no code implementations • 25 Apr 2019 • Gregory P. Meyer, Jake Charland, Darshan Hegde, Ankit Laddha, Carlos Vallespi-Gonzalez

In this paper, we present an extension to LaserNet, an efficient and state-of-the-art LiDAR based 3D object detector.

3D Object Detection 3D Semantic Segmentation +1

LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving

no code implementations • CVPR 2019 • Gregory P. Meyer, Ankit Laddha, Eric Kee, Carlos Vallespi-Gonzalez, Carl K. Wellington

The efficiency results from processing LiDAR data in the native range view of the sensor, where the input data is naturally compact.

3D Object Detection Autonomous Driving +1

Robust Model-Based 3D Head Pose Estimation

no code implementations • ICCV 2015 • Gregory P. Meyer, Shalini Gupta, Iuri Frosio, Dikpal Reddy, Jan Kautz

We introduce a method for accurate three dimensional head pose estimation using a commodity depth camera.

Face Model Head Pose Estimation