Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera

Jia, Dan; Steinweg, Mats; Hermans, Alexander; Leibe, Bastian

doi:10.1109/icra48506.2021.9561699

Cited by 8 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In that study, low-cost 2D-lidar-not the expensive 3D-lidar-was combined with a camera. Among the studies related to 2D-lidar, a study that combines 2D-lidar with a camera [31] classifies human objects based on the camera. Humans are detected in 2D-lidar by matching them with the components scanned by 2D-lidar.…”

Section: Robot and Sensormentioning

confidence: 99%

Intelligent SLAM Algorithm Fusing Low-Cost Sensors at Risk of Building Collapses

Kim¹,

Ahn²

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

When firefighters search inside a building that is at risk of collapse due to abandonment or disasters such as fire, they use old architectural drawings or a simple monitoring method involving a video device attached to a robot. However, using these methods, the disaster situation inside a building at risk of collapse is difficult to detect and identify. Therefore, we investigate the generation of digital maps for a disaster site to accurately analyze internal situations. In this study, a robot combined with a low-cost camera and twodimensional light detection and ranging (2D-lidar) traverses across a floor to estimate the location of obstacles while drawing an internal map of the building. We propose an algorithm that detects the floor and then determines the possibility of entry, tracks collapses, and detects obstacles by analyzing patterns on the floor. The robot's location is estimated, and a digital map is created based on Hector simultaneous localization and mapping (SLAM). Subsequently, the positions of obstacles are estimated based on the range values detected by 2D-lidar, and the position of the obstacles are identified on the map using the map update method in semantic SLAM. All equipment are implemented using low-specification devices, and the experiments are conducted using a low-cost robot that affords near-real-time performance. The experiments are conducted in various actual internal environments of buildings. In terms of obstacle detection performance, almost all obstacles are detected, and their positions identified on the map with a high accuracy of 89%.

show abstract

Section: Robot and Sensormentioning

confidence: 99%

Intelligent SLAM Algorithm Fusing Low-Cost Sensors at Risk of Building Collapses

Kim¹,

Ahn²

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…Most recent developments [5,6,21,22] resorted to deeplearning techniques by applying 1D CNNs to range data, and no longer require motion-based filtering. The first of these approaches is the DROW detector [5].…”

Section: Related Workmentioning

confidence: 99%

“…It was originally designed to detect walking aids, and was later extended to also detect persons [6]. The current state-ofthe-art method is the DR-SPAAM detector [21,22], which augments the DROW detector with a temporal aggregation paradigm, incorporating information over sequential Li-DAR scans in order to improve the detection performance.…”

Section: Related Workmentioning

confidence: 99%

“…They are mounted at the height of the lower legs, and their scans are merged to a single 360 • scan, having 1091 points. Jia et al [22] used these scans to evaluate 2D-LiDAR-based person detectors, by synchronizing and aligning them to the 3D annotations. In this work, we use 2D LiDAR scans from JRDB, following the same data preparation procedure.…”

Section: Datasetsmentioning

confidence: 99%

“…In the case of fine-tuning a pretrained network, we reduce the training duration to 10 epochs. 2 To train DR-SPAAM on JRDB, we follow the procedures from [22], and train the network for 20 epochs with a batch size of 6, using the same pre and postprocessing hyperparameters. The original DR-SPAAM only predicts x, y locations of the person, providing no information related to bounding boxes.…”

Section: Training Setupmentioning

confidence: 99%

See 2 more Smart Citations

2D vs. 3D LiDAR-based Person Detection on Mobile Robots

Jia¹,

Hermans²,

Leibe³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Person detection is a crucial task for mobile robots navigating in human-populated environments and LiDAR sensors are promising for this task, given their accurate depth measurements and large field of view. This paper studies existing LiDAR-based person detectors with a particular focus on mobile robot scenarios (e.g. service robot or social robot), where persons are observed more frequently and in much closer ranges, compared to the driving scenarios. We conduct a series of experiments, using the recently released JackRabbot dataset and the state-of-the-art detectors based on 3D or 2D LiDAR sensors (CenterPoint and DR-SPAAM respectively). These experiments revolve around the domain gap between driving and mobile robot scenarios, as well as the modality gap between 3D and 2D LiDAR sensors. For the domain gap, we aim to understand if detectors pretrained on driving datasets can achieve good performance on the mobile robot scenarios, for which there are currently no trained models readily available. For the modality gap, we compare detectors that use 3D or 2D LiDAR, from various aspects, including performance, runtime, localization accuracy, robustness to range and crowdedness. The results from our experiments provide practical insights into LiDAR-based person detection and facilitate informed decisions for relevant mobile robot designs and applications.

show abstract

Multiposture leg tracking for temporarily vision restricted environments based on fusion of laser and radar sensor data

Mandischer

Hou

Corves

2023

Journal of Field Robotics

View full text Add to dashboard Cite

Leg tracking is an established field in mobile robotics and machine vision in general.These algorithms, however, only distinguish the scene between leg and nonleg detections. In application fields like firefighting, where people tend to choose squatting or crouching over standing postures, those methods will inevitably fail.Further, tracking based on a single sensor system may reduce the overall reliability if brought to outdoor or complex environments with limited vision on the target objectives. Therefore, we extend our recent work to a multiposture detection system based on laser and radar sensors, that are fused to allow for maximal reliability and accuracy in scenarios as complex as indoor firefighting with vastly limited vision. The proposed tracking pipeline is trained and extensively validated on a new data set. We show that the radar tracker reaches state-of-the-art performance, and that laser and fusion tracker outperform recent methods.

show abstract

Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera

Cited by 8 publications

References 18 publications

Intelligent SLAM Algorithm Fusing Low-Cost Sensors at Risk of Building Collapses

Intelligent SLAM Algorithm Fusing Low-Cost Sensors at Risk of Building Collapses

2D vs. 3D LiDAR-based Person Detection on Mobile Robots

Multiposture leg tracking for temporarily vision restricted environments based on fusion of laser and radar sensor data

Contact Info

Product

Resources

About