-
Trajectory Prediction Based on Roadside Millimeter Wave Radar and Video Fusion
-
LiRaNet: End-to-End Trajectory Prediction using Spatio-Temporal Radar Fusion
-
Learning to Track Multiple Radar Targets with Long Short-Term Memory Networks
-
Trajectory Prediction Method of Millimeter-Wave Radar Based on Markov Model for Roadside Installation Scenario
-
Predicting Vehicle Behavior Using Automotive Radar and Recurrent Neural Networks
Radar 데이터를 사용하여 Trajectory Prediction을 수행하는 연구에 대한 조사
이 분야는 주로 aircraft를 target으로 하는 연구가 주를 이루는 것으로 보인다.
하지만, 도로 상의 객체를 target으로 하는 연구도 존재하는데 이러한 연구들은 센서 융합 기반의 방식을 사용하여 Radar뿐 아니라 camera나 LiDAR를 같이 사용하는 것으로 보인다.
Trajectory Prediction Based on Roadside Millimeter Wave Radar and Video Fusion
https://ieeexplore.ieee.org/abstract/document/9725037
Trajectory Prediction Based on Roadside Millimeter Wave Radar and Video Fusion
In recent years, with the development of intelligent transportation system, roadside service is more and more widely used in urban road transportation system. Based on the roadside millimeter wave radar and camera, this paper obtains the motion trajectory
ieeexplore.ieee.org
센서: Radar, camera
Tracking: Deep Sort
Prediction: LSTM network
특징: single target에 대한 prediction으로 보인다.
LiRaNet: End-to-End Trajectory Prediction using Spatio-Temporal Radar Fusion
https://arxiv.org/abs/2010.00731
LiRaNet: End-to-End Trajectory Prediction using Spatio-Temporal Radar Fusion
In this paper, we present LiRaNet, a novel end-to-end trajectory prediction method which utilizes radar sensor information along with widely used lidar and high definition (HD) maps. Automotive radar provides rich, complementary information, allowing for l
arxiv.org
센서: Radar, LiDAR, HD map
특징: head에서 single, multi path hypothesis 추출이 가능
Learning to Track Multiple Radar Targets with Long Short-Term Memory Networks
https://www.hindawi.com/journals/wcmc/2023/1033371/
Learning to Track Multiple Radar Targets with Long Short-Term Memory Networks
Radar multitarget tracking in a dense clutter environment remains a complex problem to be solved. Most existing solutions still rely on complex motion models and prior distribution knowledge. In this paper, a new online tracking method based on a long shor
www.hindawi.com
센서: Radar
Prediction: LSTM network
특징: state prediction, measurement association, and trajectory management functions in an end-to-end manner.
Trajectory Prediction Method of Millimeter-Wave Radar Based on Markov Model for Roadside Installation Scenario
https://ieeexplore.ieee.org/abstract/document/10016148
Trajectory Prediction Method of Millimeter-Wave Radar Based on Markov Model for Roadside Installation Scenario
In the application of roadside traffic detection, when the wide-area millimeter-wave radar detects the target, due to the limits of target occlusion, detection angle and detection range, the problem of missing target trajectory points will be inevitable. A
ieeexplore.ieee.org
센서:Radar
Prediction: Markov Model
특징: radial distance, radial speed, horizontal distance and horizontal speed 네 가지 값 예측
Predicting Vehicle Behavior Using Automotive Radar and Recurrent Neural Networks
https://ieeexplore.ieee.org/abstract/document/9520242
Predicting Vehicle Behavior Using Automotive Radar and Recurrent Neural Networks
We present a Long Short Term Memory (LSTM) encoder-decoder architecture to anticipate the future positions of vehicles in a road network given several seconds of historical observations and associated map features. Unlike existing architectures, the propos
ieeexplore.ieee.org
센서: Radar
Prediction: LSTM network
the first task encodes a feature given the past observations.
the second task estimates future maneuvers given the encoded state.
the third task predicts the future motion given the estimated maneuvers and the initially encoded states.
the fourth task estimates future trajectory given the encoded state and the predicted maneuvers and motions.
'Paradigm' 카테고리의 다른 글
| 3D MOT에서 JDE 적용이 어려운 이유 (0) | 2023.11.26 |
|---|---|
| 센서 융합 기술의 현 주소 (0) | 2023.11.10 |
| 3D MOT - Joint Detection and Tracking (0) | 2023.10.25 |
Radar 데이터를 사용하여 Trajectory Prediction을 수행하는 연구에 대한 조사
이 분야는 주로 aircraft를 target으로 하는 연구가 주를 이루는 것으로 보인다.
하지만, 도로 상의 객체를 target으로 하는 연구도 존재하는데 이러한 연구들은 센서 융합 기반의 방식을 사용하여 Radar뿐 아니라 camera나 LiDAR를 같이 사용하는 것으로 보인다.
Trajectory Prediction Based on Roadside Millimeter Wave Radar and Video Fusion
https://ieeexplore.ieee.org/abstract/document/9725037
Trajectory Prediction Based on Roadside Millimeter Wave Radar and Video Fusion
In recent years, with the development of intelligent transportation system, roadside service is more and more widely used in urban road transportation system. Based on the roadside millimeter wave radar and camera, this paper obtains the motion trajectory
ieeexplore.ieee.org
센서: Radar, camera
Tracking: Deep Sort
Prediction: LSTM network
특징: single target에 대한 prediction으로 보인다.
LiRaNet: End-to-End Trajectory Prediction using Spatio-Temporal Radar Fusion
https://arxiv.org/abs/2010.00731
LiRaNet: End-to-End Trajectory Prediction using Spatio-Temporal Radar Fusion
In this paper, we present LiRaNet, a novel end-to-end trajectory prediction method which utilizes radar sensor information along with widely used lidar and high definition (HD) maps. Automotive radar provides rich, complementary information, allowing for l
arxiv.org
센서: Radar, LiDAR, HD map
특징: head에서 single, multi path hypothesis 추출이 가능
Learning to Track Multiple Radar Targets with Long Short-Term Memory Networks
https://www.hindawi.com/journals/wcmc/2023/1033371/
Learning to Track Multiple Radar Targets with Long Short-Term Memory Networks
Radar multitarget tracking in a dense clutter environment remains a complex problem to be solved. Most existing solutions still rely on complex motion models and prior distribution knowledge. In this paper, a new online tracking method based on a long shor
www.hindawi.com
센서: Radar
Prediction: LSTM network
특징: state prediction, measurement association, and trajectory management functions in an end-to-end manner.
Trajectory Prediction Method of Millimeter-Wave Radar Based on Markov Model for Roadside Installation Scenario
https://ieeexplore.ieee.org/abstract/document/10016148
Trajectory Prediction Method of Millimeter-Wave Radar Based on Markov Model for Roadside Installation Scenario
In the application of roadside traffic detection, when the wide-area millimeter-wave radar detects the target, due to the limits of target occlusion, detection angle and detection range, the problem of missing target trajectory points will be inevitable. A
ieeexplore.ieee.org
센서:Radar
Prediction: Markov Model
특징: radial distance, radial speed, horizontal distance and horizontal speed 네 가지 값 예측
Predicting Vehicle Behavior Using Automotive Radar and Recurrent Neural Networks
https://ieeexplore.ieee.org/abstract/document/9520242
Predicting Vehicle Behavior Using Automotive Radar and Recurrent Neural Networks
We present a Long Short Term Memory (LSTM) encoder-decoder architecture to anticipate the future positions of vehicles in a road network given several seconds of historical observations and associated map features. Unlike existing architectures, the propos
ieeexplore.ieee.org
센서: Radar
Prediction: LSTM network
the first task encodes a feature given the past observations.
the second task estimates future maneuvers given the encoded state.
the third task predicts the future motion given the estimated maneuvers and the initially encoded states.
the fourth task estimates future trajectory given the encoded state and the predicted maneuvers and motions.
'Paradigm' 카테고리의 다른 글
| 3D MOT에서 JDE 적용이 어려운 이유 (0) | 2023.11.26 |
|---|---|
| 센서 융합 기술의 현 주소 (0) | 2023.11.10 |
| 3D MOT - Joint Detection and Tracking (0) | 2023.10.25 |
