The H3D Dataset for Full-Surround 3D Multi-Object Detection and Tracking in Crowded Urban Scenes

Patil, Abhishek; Malla, Srikanth; Gang, Haiming; Chen, Yi-Ting

doi:10.48550/arxiv.1903.01568

Cited by 8 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the fast development of the deep network based point cloud processing methods [26], [27], [33] and sparse convolution [21], [13], [14], [16], [15], various algorithms [37], [31], [35], [19] are developed to efficiently detect object in point clouds. The advantages of the LiDAR sensors and the algorithms make them indispensable components for modern autonomous driving systems, algorithms [1], [6], [19], [20], [32], [35], [37], and multi-modality datasets [3], [7], [8], [12], [25]. KITTI [12] provides over 7K annotated samples collected with cameras and LiDAR.…”

Section: Related Workmentioning

confidence: 99%

Cirrus: A Long-range Bi-pattern LiDAR Dataset

Wang

Ding

Liu

et al. 2020

Preprint

View full text Add to dashboard Cite

In this paper, we introduce Cirrus, a new longrange bi-pattern LiDAR public dataset for autonomous driving tasks such as 3D object detection, critical to highway driving and timely decision making. Our platform is equipped with a high-resolution video camera and a pair of LiDAR sensors with a 250-meter effective range, which is significantly longer than existing public datasets. We record paired point clouds simultaneously using both Gaussian and uniform scanning patterns. Point density varies significantly across such a long range, and different scanning patterns further diversify object representation in LiDAR. In Cirrus, eight categories of objects are exhaustively annotated in the LiDAR point clouds for the entire effective range. To illustrate the kind of studies supported by this new dataset, we introduce LiDAR model adaptation across different ranges, scanning patterns, and sensor devices.Promising results show the great potential of this new dataset to the robotics and computer vision communities.

show abstract

Section: Related Workmentioning

confidence: 99%

Cirrus: A Long-range Bi-pattern LiDAR Dataset

Wang

Ding

Liu

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…These datasets are typically created from a stationary surveillance camera [27,37,34], or from aerial views obtained from a static drone-mounted camera [41]. In driving scenes, the 3D point cloud-based datasets [15,36,23,5,1,9] were originally introduced for detection, tracking, etc., but recently used for vehicle trajectory prediction as well. Also, [58,8] provide RGB images captured from an egocentric view of a moving vehicle and applied to future trajectory forecast problem.…”

Section: Datasetsmentioning

confidence: 99%

TITAN: Future Forecast using Action Priors

Malla¹,

Dariush²,

Choi³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

We consider the problem of predicting the future trajectory of scene agents from egocentric views obtained from a moving platform. This problem is important in a variety of domains, particularly for autonomous systems making reactive or strategic decisions in navigation. In an attempt to address this problem, we introduce TITAN (Trajectory Inference using Targeted Action priors Network), a new model that incorporates prior positions, actions, and context to forecast future trajectory of agents and future ego-motion. In the absence of an appropriate dataset for this task, we created the TITAN dataset that consists of 700 labeled video-clips (with odometry) captured from a moving vehicle on highly interactive urban traffic scenes in Tokyo. Our dataset includes 50 labels including vehicle states and actions, pedestrian age groups, and targeted pedestrian action attributes that are organized hierarchically corresponding to atomic, simple/complex-contextual, transportive, and communicative actions. To evaluate our model, we conducted extensive experiments on the TITAN dataset, revealing significant performance improvement against baselines and state-of-the-art algorithms. We also report promising results from our Agent Importance Mechanism (AIM), a module which provides insight into assessment of perceived risk by calculating the relative influence of each agent on the future ego-trajectory. The dataset is available at https://usa.honda-ri.com/titan

show abstract

“…In this process, NEMO generates multi-modal future motions of the target over the uncertainty of future ego-motion, which is reflective of real-world egocentric interactions. For more accurate ego-motion prediction, we release new IMU data for HEV-I [5], which can extend its use far beyond the future object localization problem to visual odometry estimate [14] and other 2D image-based control learning tasks [15], [16]. The updated IMU sensor data will be made available at https://usa.honda-ri.com/hevi…”

Section: Introductionmentioning

confidence: 99%

NEMO: Future Object Localization Using Noisy Ego Priors

Malla¹,

Dwivedi²,

Dariush³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Predictive models for forecasting future behavior of road agents should consider the multi-modal nature and be aware of the uncertainty of their predictions. Particularly from the egocentric view where the motion of other agents is captured with respect to the ego-motion, the uncertainty of ego-motion prediction is critical to determine their interactive reactions and behaviors. Along this line, we propose NEMO (Noisy Ego MOtion priors for future object localization) for future forecast of road agents in the egocentric view. A predictive distribution of future forecast is jointly modeled with the uncertainty of predictions. For this, we divide the problem into two tasks: future ego-motion prediction and future object localization. We first model the multi-modal distribution of future ego-motion with uncertainty estimates. The resulting distribution of egobehavior is used to sample multiple modes of future egomotion. Then, each modality is used as a prior to understand the interactions between the ego-vehicle and target agent. We predict the multi-modal future locations of the target from individual modes of the ego-vehicle, modeling the uncertainty of target's behavior. To this end, we extensively evaluate the proposed framework using the publicly available benchmark dataset (HEV-I) with an addition of Inertial Measurement Unit (IMU) data to it.

show abstract

The H3D Dataset for Full-Surround 3D Multi-Object Detection and Tracking in Crowded Urban Scenes

Cited by 8 publications

References 22 publications

Cirrus: A Long-range Bi-pattern LiDAR Dataset

Cirrus: A Long-range Bi-pattern LiDAR Dataset

TITAN: Future Forecast using Action Priors

NEMO: Future Object Localization Using Noisy Ego Priors

Contact Info

Product

Resources

About