Robust Scene Recognition Research Articles

Multicriteria-Based Active Discriminative Dictionary Learning for Scene Recognition

Scene recognition is a significant and challenging problem in the field of computer vision. One of the principal bottlenecks in applying machine learning techniques to scene recognition tasks is the requirement of a large number of labeled training data. However, labeling massive training data manually (especially labeling images and videos) is very expensive in terms of human time and effort. In this paper, we present a novel multicriteria-based active discriminative dictionary learning (M-ADDL) algorithm to reduce the human annotation effort and create a robust scene recognition model. The M-ADDL algorithm possesses three advantages. First, M-ADDL introduces an active learning strategy into the discriminative dictionary learning model so that the performance of discriminative dictionary learning can be improved when the number of labeled samples is small. Second, different from most existing active learning methods that measure either the informativeness or representativeness of unlabeled samples to select useful samples for expanding the training dataset, M-ADDL employs both informativeness and representativeness to query useful unlabeled samples and utilizes the manifold-preserving ability of unlabeled samples as an additional sample selection criterion. Finally, a more effective representativeness criterion is presented based on the reconstruction coefficients of the samples. The experimental results of four standard scene recognition databases demonstrate the feasibility and validity of the proposed M-ADDL algorithm.

走行ロボットの視覚特性を考慮した姿勢誤差にロバストな地点認識

走行ロボットの視覚特性を考慮した姿勢誤差にロバストな地点認識

Robust scene recognition using a GA and real-world raw-image

This paper presents a new concept of scene recognition by a genetic algorithm (GA), using the 2-D gray-scale image of a working space, termed here as raw-image, and a model shaping the 2-D top-surface of a target object. In fact here, the problem of object recognition in the raw-image is changed into an optimization problem of a model-based evaluation function. We make use in this research of a GA, as a search and optimization method. This GA employs a model-based fitness function as its objective function to perform the search of a target in the raw-image. In this research, three object models, namely a frame model, a surface model, and a surface-strips model are investigated in order to determine which one is the best for scene recognition in a noisy environment. Also, in order to appraise the recognition performance of each model, a comparative study is performed by analyzing the answers to the following criteria questions: sensitivity, reliability, and speed. The effectiveness of the method has been verified through experiments using real-world raw-images, and the method has shown its robustness of object recognition with the surface-strips model, in spite of the noises in the scene.