We describe and validate a simple context-based scene recognition algorithm for mobile robotics applications. The system can differentiate outdoor scenes from various sites on a college campus using a multiscale set of early-visual features, which capture the "gist" of the scene into a low-dimensional signature vector. Distinct from previous approaches, the algorithm presents the advantage of being biologically plausible and of having low-computational complexity, sharing its low-level features with a model for visual attention that may operate concurrently on a robot. We compare classification accuracy using scenes filmed at three outdoor sites on campus (13,965 to 34,711 frames per site). Dividing each site into nine segments, we obtain segment classification rates between 84.21 percent and 88.62 percent. Combining scenes from all sites (75,073 frames in total) yields 86.45 percent correct classification, demonstrating the generalization and scalability of the approach

Rapid Biologically-Inspired Scene Classification Using Features Shared with Visual Attention

We present context-based scene recognition for mobile robotics applications. Our classifier is able to differentiate outdoor scenes without temporal filtering relatively well from a variety of locations at a college campus using a set of features that together capture the "gist" of the scene. We compare the classification accuracy of a set of scenes from 1551 frames filmed outdoors along a path and dividing them to four and twelve different legs while obtaining a classifi- cation rate of 67.96 percent and 48.61 percent, respectively. We also tested the scalability of the features by comparing the classification results from the previous scenes with four legs with a longer path with eleven legs while obtaining a classification rate of 55.08 percent. In the end, some ideas are put forth to improve the theoretical strength of the gist features.

Gist: A Mobile Robotics Application of Context-Based Vision in Outdoor Environment

The purpose of our research is a realization of the autonomy to deal with the real environment of mobile robots. In this paper, the concept of the autonomy in the robot is discussed first, the "long term activity" as a benchmark problem for the autonomous mobile robot is proposed, and the elementary technologies to realize a autonomous robot with such an ability is considered. Our mobile robot Yamabico-Liv which is being constructed for the experiments of long time activity is also presented.

Long term activity of the autonomous robot-proposal of a bench-mark problem for the autonomy

A novel Position-Invariant Robust Feature, designated as PIRF, is presented to address the problem of highly dynamic scene recognition. The PIRF is obtained by identifying existing local features (i.e. SIFT) that have a wide baseline visibility within a place (one place contains more than one sequential images). These wide-baseline visible features are then represented as a single PIRF, which is computed as an average of all descriptors associated with the PIRF. Particularly, PIRFs are robust against highly dynamical changes in scene: a single PIRF can be matched correctly against many features from many dynamical images. This paper also describes an approach to using these features for scene recognition. Recognition proceeds by matching an individual PIRF to a set of features from test images, with subsequent majority voting to identify a place with the highest matched PIRF. The PIRF system is trained and tested on 2000+ outdoor omnidirectional images and on COLD datasets. Despite its simplicity, PIRF offers a markedly better rate of recognition for dynamic outdoor scenes (ca. 90%) than the use of other features. Additionally, a robot navigation system based on PIRF (PIRF-Nav) can outperform other incremental topological mapping methods in terms of time (70% less) and memory. The number of PIRFs can be reduced further to reduce the time while retaining high accuracy, which makes it suitable for long-term recognition and localization.

https://haselab.info/calculation/img/pdf/02_PIRF.pdf

Position-Invariant Robust Features for Long-Term Recognition of Dynamic Outdoor Scenes

The three-dimensional localization problem of outdoor mobile robots is a primary issue for autonomous navigation applications, since the accuracy of positioning will affect the incoming mapping and path planning tasks heavily In this paper, using INS, encoder and laser LiDAR as the main means for pose perception, a laser LiDAR aided odometry approach based on the normal distributions transform(NDT) scan matching approach is proposed to improve the precision of pose estimates for a mobile robot in GPS denied outdoor environments The 3D kinematic model of the mobile robot is developed so that the IMU and the encoder data can be fused firstly to obtain the initial localization result with dead reckoning technologies On that basis, the three-dimensional NDT scan matching method is introduced to compute the pose transformation matrix in real-time using the adjacent two depth frames from LiDAR data, which can get fine pose estimates by calibrate the accumulation errors periodically Experiments results show the correctness and validity of the presented method

A LiDAR Odometry for Outdoor Mobile Robots Using NDT Based Scan Matching in GPS-denied environments

In this paper, we report a development of an autonomous mobile robot for long distance outdoor navigation in our university campus. We propose how to generate a long distance Perceived Route Map (PRM), a position-based navigation algorithm using PRM, and incremental integration of the robot system by multiple processors and multiple agents. Furthermore, we developed an experimental robot system and conducted experiments of autonomous navigation using PRM in our university campus. Finally, from experimental results, we discuss open problems and future work in outdoor navigation.

Shin

Papers

Long distance outdoor navigation of an autonomous mobile robot by playback of Perceived Route Map