Outdoor intersection detection for autonomous exploration

Mukhija, Piyoosh; Tourani, Siddharth; Krishna, K. Madhava

doi:10.1109/itsc.2012.6338647

Cited by 10 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several intersection classification models have been tested using a variety of external input, such as images [1][2][3][4][5][6][7], videos [8], global positioning system (GPS) data [9], light detection and ranging [10,11], or combinations thereof [2,[12][13][14][15]. In this work, we use images as input owing to the simplicity and low cost (e.g., hardware, labor, and computation).…”

Section: Intersection Classificationmentioning

confidence: 99%

Assembling three one‐camera images for three‐camera intersection classification

Astrid,

Lee

2023

ETRI Journal

View full text Add to dashboard Cite

Determining whether an autonomous self‐driving agent is in the middle of an intersection can be extremely difficult when relying on visual input taken from a single camera. In such a problem setting, a wider range of views is essential, which drives us to use three cameras positioned in the front, left, and right of an agent for better intersection recognition. However, collecting adequate training data with three cameras poses several practical difficulties; hence, we propose using data collected from one camera to train a three‐camera model, which would enable us to more easily compile a variety of training data to endow our model with improved generalizability. In this work, we provide three separate fusion methods (feature, early, and late) of combining the information from three cameras. Extensive pedestrian‐view intersection classification experiments show that our feature fusion model provides an area under the curve and F1‐score of 82.00 and 46.48, respectively, which considerably outperforms contemporary three‐ and one‐camera models.

show abstract

Section: Intersection Classificationmentioning

confidence: 99%

Assembling three one‐camera images for three‐camera intersection classification

Astrid,

Lee

2023

ETRI Journal

View full text Add to dashboard Cite

show abstract

“…In [7], data from camera is fused with rangefinder data. Then techniques from image processing and computational geometry are used to extract a skeleton navigable region, thus providing the intersections.…”

Section: Introductionmentioning

confidence: 99%

Road junction detection from 3D point clouds

Habermann

Vido

Osorio

et al. 2016

2016 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Detecting changing traffic conditions is of primal importance for the safety of autonomous cars navigating in urban environments. Among the traffic situations that require more attention and careful planning, road junctions are the most significant. This work presents an empirical study of the application of well known machine learning techniques to create a robust method for road junction detection. Features are extracted from 3D pointclouds corresponding to single frames of data collected by a laser rangefinder. Three well known classifiers-support vector machines, adaptive boosting and artificial neural networks-are used to classify them into "junctions" or "roads". The best performing classifier is used in the next stage, where structured classifiers-hidden Markov models and conditional random fields-are used to incorporate contextual information, in an attempt to improve the performance of the method. We tested and compared these approaches on datasets from two different 3D laser scanners, and in two different countries, Germany and Brazil.

show abstract

“…To accomplish this, the map is required to provide the appropriate information on the terrain surrounding. So far, many researches have been carried out about 2D and 3D map building in indoor and outdoor [1][2][3][4][5]. Currently many studies have been conducted concerning the vision sensor, ultrasonic sensor and laser scanner.…”

Section: Introductionmentioning

confidence: 99%

Impulse noise removal of LRF for 3D map building using a hybrid median filter

Hwang

Choi

Kim

et al. 2013

2013 IEEE International Conference on Industrial Technology (ICIT)

View full text Add to dashboard Cite

In this paper, a single LRF has been used to produce a 3D map for the mobile robot navigation. The 2D laser scanners are used for mobile robots navigation, where the laser scanner is applied to detect a certain level of area by the straight beam. Therefore, it is limited to the usages of 2D obstacle detection and avoidance. In this research, it is designed to complement a mobile robot system to move up and down a single LRF along the yaw axis. During the up and down motion, the 2D data is stacked and manipulated to build a 3D map. Often a single LRF data is mixed with Gaussian and impulse noises. The impulse noises are removed out by the hybrid median filter designed in this research. The 2D data which are improved by deleting the impulse noises are layered to build the 3D map. To remove impulse noises while preserving the boundary is a main advantage of the hybrid median filter which has been used widely to improve the quality of images. The effectiveness of this hybrid median filter for rejecting the impulse noises has been verified through the real experiments. The performance of the hybrid median filter is evaluated in terms of PSNR (peak signal to noise ratio) and the processing time.

show abstract

Outdoor intersection detection for autonomous exploration

Cited by 10 publications

References 9 publications

Assembling three one‐camera images for three‐camera intersection classification

Assembling three one‐camera images for three‐camera intersection classification

Road junction detection from 3D point clouds

Impulse noise removal of LRF for 3D map building using a hybrid median filter

Contact Info

Product

Resources

About