Semantic Segmentation of Aerial Images in Urban Areas With Class-Specific Higher-Order Cliques

Montoya-Zegarra, Javier A.; Wegner, Jan Dirk; Ladický, Ľubor; Schindler, Konrad

doi:10.5194/isprsannals-ii-3-w4-127-2015

Cited by 38 publications

(21 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to this work, Montoya-Zegarra et al explored road mapping 44 and the semantic segmentation of aerial images with higher-order cliques. 43 In our work we are more focused on segmenting images captured from low-flying UAV, the outputs of which need to be used for planning UGV missions to search for sources of radiation. Radford studied the problem of real-time roadway classification from aerial imagery for UGV path planning, 53 where k-means clustering and image mosaicking were used.…”

Section: Scene Understandingmentioning

confidence: 99%

Radiation search operations using scene understanding with autonomous UAV and UGV

Christie

Shoemaker

Kochersberger

et al. 2017

Journal of Field Robotics

View full text Add to dashboard Cite

Autonomously searching for hazardous radiation sources requires the ability of the aerial and ground systems to understand the scene they are scouting. In this paper, we present systems, algorithms, and experiments to perform radiation search using unmanned aerial vehicles (UAV) and unmanned ground vehicles (UGV) by employing semantic scene segmentation. The aerial data is used to identify radiological points of interest, generate an orthophoto along with a digital elevation model (DEM) of the scene, and perform semantic segmentation to assign a category (e.g. road, grass) to each pixel in the orthophoto. We perform semantic segmentation by training a model on a dataset of images we collected and annotated, using the model to perform inference on images of the test area unseen to the model, and then refining the results with the DEM to better reason about category predictions at each pixel. We then use all of these outputs to plan a path for a UGV carrying a LiDAR to map the environment and avoid obstacles not present during the flight, and a radiation detector to collect more precise radiation measurements from the ground. Results of the analysis for each scenario tested favorably. We also note that our approach is general and has the potential to work for a variety of different sensing tasks.

show abstract

Section: Scene Understandingmentioning

confidence: 99%

Radiation search operations using scene understanding with autonomous UAV and UGV

Christie

Shoemaker

Kochersberger

et al. 2017

Journal of Field Robotics

View full text Add to dashboard Cite

show abstract

“…In this type of method, image segmentation is the first and a critical step. Many image segmentation methods have been proposed, such as, watershed (Beucher and Meyer, 1993), graph cut (Boykov and Jolly, 2001), mean shift (Comaniciu and Meer, 2002), MST (Felzenszwalb and Huttenlocher, 2004), etc., and many method developed on them for example Hu et al (2005), Cui and Zhang (2011), Montoya-Zegarra et al (2015) etc., but the uncertainty of segmentation and especially the optimal segmentation scale is the common problem which is still difficult to resolve just because of the diversity of targets in large area images. Ming et al (2008) proposed the segmentation scale selection method, but the segmentation results usually can't fit with all the targets.…”

Section: Motivationmentioning

confidence: 99%

SPMK and Grabcut Based Target Extraction From High Resolution Remote Sensing Images

Cui¹,

Wang²,

Feng³

et al. 2016

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

View full text Add to dashboard Cite

ABSTRACT:Target detection and extraction from high resolution remote sensing images is a basic and wide needed application. In this paper, to improve the efficiency of image interpretation, we propose a detection and segmentation combined method to realize semi-automatic target extraction. We introduce the dense transform color scale invariant feature transform (TC-SIFT) descriptor and the histogram of oriented gradients (HOG) & HSV descriptor to characterize the spatial structure and color information of the targets. With the kmeans cluster method, we get the bag of visual words, and then, we adopt three levels' spatial pyramid (SP) to represent the target patch. After gathering lots of different kinds of target image patches from many high resolution UAV images, and using the TC-SIFT-SP and the multi-scale HOG & HSV feature, we constructed the SVM classifier to detect the target. In this paper, we take buildings as the targets. Experiment results show that the target detection accuracy of buildings can reach to above 90%. Based on the detection results which are a series of rectangle regions of the targets. We select the rectangle regions as candidates for foreground and adopt the GrabCut based and boundary regularized semi-auto interactive segmentation algorithm to get the accurate boundary of the target. Experiment results show its accuracy and efficiency. It can be an effective way for some special targets extraction.

show abstract

“…High altitude, high resolution aerial images are frequently used to perform terrain classification [7], [8], [9]. However, none of these approaches consider ground robot guidance or path planning, and do not operate using active vision.…”

Section: Related Workmentioning

confidence: 99%

Active Autonomous Aerial Exploration for Ground Robot Path Planning

Delmerico

Mueggler

Nitsch

et al. 2017

IEEE Robot. Autom. Lett.

121

View full text Add to dashboard Cite

Abstract-We address the problem of planning a path for a ground robot through unknown terrain, using observations from a flying robot. In search and rescue missions, which are our target scenarios, the time from arrival at the disaster site to the delivery of aid is critically important. Previous works required exhaustive exploration before path planning, which is time-consuming but eventually leads to an optimal path for the ground robot. Instead, we propose active exploration of the environment, where the flying robot chooses regions to map in a way that optimizes the overall response time of the system, which is the combined time for the air and ground robots to execute their missions. In our approach, we estimate terrain classes throughout our terrain map, and we also add elevation information in areas where the active exploration algorithm has chosen to perform 3D reconstruction. This terrain information is used to estimate feasible and efficient paths for the ground robot. By exploring the environment actively, we achieve superior response times compared to both exhaustive and greedy exploration strategies. We demonstrate the performance and capabilities of the proposed system in simulated and real-world outdoor experiments. To the best of our knowledge, this is the first work to address ground robot path planning using active aerial exploration.

show abstract

Semantic Segmentation of Aerial Images in Urban Areas With Class-Specific Higher-Order Cliques

Cited by 38 publications

References 36 publications

Radiation search operations using scene understanding with autonomous UAV and UGV

Radiation search operations using scene understanding with autonomous UAV and UGV

SPMK and Grabcut Based Target Extraction From High Resolution Remote Sensing Images

Active Autonomous Aerial Exploration for Ground Robot Path Planning

Contact Info

Product

Resources

About