People Detection in 3d Point Clouds Using Local Surface Normals

Hegger, Frederik; Hochgeschwender, Nico; Kraetzschmar, Gerhard K.; Ploeger, Paul G.

doi:10.1007/978-3-642-39250-4_15

Cited by 16 publications

(17 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Histogram of Local Surface Normals (HLSN [17]): an alternative classification feature extracted from 3D points.…”

Section: Alternative Methodsmentioning

confidence: 99%

“…A relevant related work [17] faces the problem of people detection in presence of occlusions, by splitting the 3D point cloud in layers according to the height from the floor, then finding clusters in each layer and classifying each cluster as a human segment or not: different clusters classified to be part of an human are finally connected according to their relative distance in order to reconstruct the visible part of the person. However, only occlusions affecting the lower part of the subject are considered (conversely, in our scenario the legs are often the only visible part, which raises a number of challenging issues detailed in the rest of the paper), and each frame is independently processed: instead, our method adopts tracking at different levels of the pipeline, which yields a significant advantage in overall accuracy, which we quantify in Section IV.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Kinect-based people detection and tracking from small-footprint ground robots

Gritti

Tarabini

Guzzi

et al. 2014

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Small-footprint mobile ground robots, such as the popular Turtlebot and Kobuki platforms, are by necessity equipped with sensors which lie close to the ground. Reliably detecting and tracking people from this viewpoint is a challenging problem, whose solution is a key requirement for many applications involving sharing of common spaces and close human-robot interaction. We present a robust solution for cluttered indoor environments, using an inexpensive RGB-D sensor such as the Microsoft Kinect or Asus Xtion. Even in challenging scenarios with multiple people in view at once and occluding each other, our system solves the person detection problem significantly better than alternative approaches, reaching a precision, recall and F1-score of 0.85, 0.81 and 0.83, respectively. Evaluation datasets, a real-time ROS-enabled implementation and demonstration videos are provided as supplementary material.

show abstract

“…Histogram of Local Surface Normals (HLSN [17]): an alternative classification feature extracted from 3D points.…”

Section: Alternative Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Kinect-based people detection and tracking from small-footprint ground robots

Gritti

Tarabini

Guzzi

et al. 2014

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

show abstract

“…Note that we focused on feature-based approaches and did not consider model-based approaches [17] or geodesic extrema [18], [19]. Feature-based approaches for people detection can be divided into histogram-based features [20]- [23] and geometrical and statistical features [24]. We expected that features which capture the surface of objects, like the Histograms of Local Surface Normals (HLNS) [23], are especially well suited since the local surface normals of fallen people should be irregular or cylindrical compared to the relatively regular, straight surfaces of artificial objects in home environments, like tables, walls, and chairs.…”

Section: Related Workmentioning

confidence: 99%

Fallen Person Detection for Mobile Robots Using 3D Depth Data

Volkhardt

Schneemann

Groß

2013

2013 IEEE International Conference on Systems, Man, and Cybernetics

View full text Add to dashboard Cite

Falling down and not managing to get up again is one of the main concerns of elderly people living alone in their home. Robotic assistance for the elderly promises to have a great potential of detecting these critical situations and calling for help. This paper presents a feature-based method to detect fallen people on the ground by a mobile robot equipped with a Kinect sensor. Point clouds are segmented, layered and classified to detect fallen people, even under occlusions by parts of their body or furniture. Different features, originally from pedestrian and object detection in depth data, and different classifiers are evaluated. Evaluation was done using data of 12 people lying on the floor. Negative samples were collected from objects similar to persons, two tall dogs, and five real apartments of elderly people. The best feature-classifier combination is selected to built a robust system to detect fallen people.

show abstract

“…The investigations in (Hegger et al, 2013) is related to humanrobot-interaction. The detection of peoples in domestic and unconstrained environments is crucial for a service robot.…”

Section: Related Workmentioning

confidence: 99%

Calibration of a Multiple Stereo and RGB-D Camera System for 3d Human Tracking

Amplianitis

Adduci

Reulke

2014

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Human Tracking in Computer Vision is a very active up-going research area. Previous works analyze this topic by applying algorithms and features extraction in 2D, while 3D tracking is quite an unexplored filed, especially concerning multi-camera systems. Our approach discussed in this paper is focused on the detection and tracking of human postures using multiple RGB-D data together with stereo cameras. We use low-cost devices, such as Microsoft Kinect and a people counter, based on a stereo system. The novelty of our technique concerns the synchronization of multiple devices and the determination of their exterior and relative orientation in space, based on a common world coordinate system. Furthermore, this is used for applying Bundle Adjustment to obtain a unique 3D scene, which is then used as a starting point for the detection and tracking of humans and extract significant metrics from the datasets acquired. In this article, the approaches are described for the determination of the exterior and absolute orientation. Subsequently, it is shown how a common point cloud is formed. Finally, some results for object detection and tracking, based on 3D point clouds, are presented.

show abstract

People Detection in 3d Point Clouds Using Local Surface Normals

Cited by 16 publications

References 12 publications

Kinect-based people detection and tracking from small-footprint ground robots

Kinect-based people detection and tracking from small-footprint ground robots

Fallen Person Detection for Mobile Robots Using 3D Depth Data

Calibration of a Multiple Stereo and RGB-D Camera System for 3d Human Tracking

Contact Info

Product

Resources

About