A Review of Recurrent Neural Network Based Camera Localization for Indoor Environments

Abstract

Camera localization involves the estimation of the camera pose of an image from a random scene. We used a single image or sequence of images or videos as the input. The output depends on the representation of the scene and method used. Several computer vision applications, such as robot navigation and safety inspection, can benefit from camera localization. Camera localization is used to determine the position of an object on the camera in an image containing multiple images in a sequence. Structure-based localization techniques have achieved considerable success owing to a combination of image matching and coordinate regression. Absolute and relative pose regression techniques can provide end-to-end learning; however, they exhibit poor accuracies. Despite the rapid growth in computer vision, there has been no thorough review of the categorization, evaluation, and synthesis of structures and regression-based techniques. Input format and loss strategies for recurrent neural networks (RNN) have not been adequately described in the literature. The main topic is indoor camera pose regression, which is a part of the camera localization techniques. First, we discuss certain application areas for camera localization. We then discuss different camera localization techniques, such as feature and structure-based, absolute and relative pose regression techniques, and simultaneous localization and mapping (SLAM). We evaluated the frequently used datasets and qualitatively compared the absolute and relative camera pose estimation approaches. Finally, we discuss potential directions for future research, such as optimizing the computational cost of the features and evaluating the end-to-end characteristics of multiple cameras.INDEX TERMS Camera pose regression, absolute pose regression, indoor positioning, camera localization, robot navigation, SLAM.

Exploration of image and 3D data segmentation methods: an exhaustive survey

“…Recurrent neural network (RNN) is a neural network architecture designed for sequential data processing [42], [43]. It utilizes feedback loops to maintain a representation of the sequence history, making it suitable for tasks like text generation, machine translation, and speech recognition.…”

Indoor Localization based on Short-Range Radar and Rotating Landmarks

“…Based on the environment sensors, either features of the surroundings can be matched with a global map [7] or relative measurements to landmarks [8]- [10] can be obtained for localization. A wide range of inside-out approaches based on cameras are available [11], in particular in many Virtual Reality (VR) systems [12]. However, the use of cameras is often a risk for the user's privacy and there is a high sensitivity to lighting conditions and occlusions.…”

Self-Localization of Guide Robots Through Image Classification

“…To accomplish precise self-localization, even in difficult and dynamic situations, deep convolutional networks with pose regression are used 9 . Imagebased indoor localization 13,14 techniques use both visual odometry and deep neural networks. This illustrates how deep learning may help mobile robots to self-localize accurately 15 .…”