Hierarchical Localization in Topological Models Under Varying Illumination Using Holistic Visual Descriptors

Abstract

In this paper, a hierarchical localization framework within indoor environments is proposed and evaluated, considering severe variations of the illumination conditions. The only source of information both to build a model of the environment and to solve the localization problem is a catadioptric vision system, which is mounted on the mobile robot. The images captured by this system are processed globally to obtain holistic descriptors. The position of the robot is estimated by comparing these descriptors with the information contained in a topological visual model, which is previously created using a clustering approach and is composed of a hierarchy of layers. Compacting the information via clustering proves to be an efficient alternative to estimate the position of the robot hierarchically and with robustness. The proposed localization strategy is tested with some sets of panoramic images, captured in large indoor environments under real operating conditions, including illumination changes that change substantially the appearance of the scenes. The results show a reasonable tradeoff computation time-accuracy when the localization is addressed in a hierarchical way.

Holistic Descriptors of Omnidirectional Color Images and Their Performance in Estimation of Position and Orientation

“…Recall-precision curves [50], [51] permit evaluating the performance of the descriptors in image association tasks. The concepts of recall and precision are defined as: recall = # of correct matches retrieved # total of correct matches (25) precision = # of correct matches retrieved # correct matches (26) This way, recall represents the ability of the descriptor to find all the correct associations, and precision the ability to find the correct associations as the number of experiments grows. Their values are between 0 (that would indicate that no correct match has been retrieved) and 1 (that would mean that the descriptor has found all the correct matches).…”

“…The first column contains the minimum Euclidean distance of each test image (min l Test ), and the result of the match (1 or 0 depending on whether it is correct or not). 5) Then, we sort the association list in ascending order using the image distance, and obtain the values of recall and precision according to (25) and (26). The distribution of the recall-precision curves provides information about the robustness of the descriptors with false positives considering a threshold in the image distance.…”

“…The descriptors included in this work are based on Discrete Fourier Transform [24], the Histogram of Oriented Gradients [25] and gist [26]. Most of the descriptors that can be found in the literature are designed to be used with greyscale images.…”

Uso de técnicas de machine learning para realizar mapping en robótica móvil

“…Para evaluar el proceso de localización jerárquica propuesto, se utilizan los clasificadores SVM y la red neuronal y los descriptores gist y CNN-fc7, dado que estas configuraciones generaron los mejores resultados en el experimento anterior. Por otro lado, para comparar con métodos llevados a cabo en trabajos previos, se propone también la localización jerárquica llevada a cabo mediante el uso de descriptores representativos para la localización gruesa (tal y como se hizo en [2]). Para este método, en primer lugar se lleva a cabo un algoritmo de clustering espectral, el cual agrupa la información de descripción con respecto a la similitud entre las imágenes.…”

“…Esta técnica ha sido utilizada previamente por otros autores como por ejemplo Mancini et al[7] para llevar a cabo una categorización de escenarios mediante un clasificador Naïve Bayes. Por otro lado, en trabajos previos ([10] y[2]) ya se ha probado el uso de estos descriptores para lle-var a cabo tareas de mapping visual. El descriptor utilizado para este estudio es extraído de la red places[16] y corresponde con la capa completamente convolucional 'fc7'.…”