Search

Crowdsourced localization using geo-spatial big data has become an effective approach for constructing smart-city-based location services with the fast growing number of Internet of Things terminals. This paper presents a self-calibrated multi-floor indoor positioning framework using a combination of Wi-Fi ranging, crowdsourced fingerprinting and low-cost sensors (SM-WRFS). The localization parameters, such as heading and altitude biases, step-length scale factor, and Wi-Fi ranging bias are autonomously calibrated to provide a more accurate forward 3D localization performance. In addition, the backward smoothing algorithm and a novel deep-learning model are applied in order to construct an autonomous and efficient crowdsourced Wi-Fi fingerprinting database using the detected quick response (QR) code-based landmarks. Finally, the adaptive extended Kalman filter is adopted to combine the corresponding location sources using different integration models to provide a precise multi-source fusion based multi-floor indoor localization performance. The real-world experiments demonstrate that the presented SM-WRFS is proven to realize precise 3D indoor positioning under different environments, and the meter-level positioning accuracy can be acquired in Wi-Fi ranging supported indoor areas.

Crowd-sensing-based localization is regarded as an effective method for providing indoor location-based services in large-scale urban areas. The performance of the crowd-sensing approach is subject to the poor accuracy of collected daily-life trajectories and the efficient combination of different location sources and indoor maps. This paper proposes a robust map-assisted 3D Indoor localization framework using crowd-sensing-based trajectory data and error ellipse-enhanced fusion (ML-CTEF). In the off-line phase, novel inertial odometry which contains the combination of 1D-convolutional neural networks (1D-CNN) and Bi-directional Long Short-Term Memory (Bi-LSTM)-based walking speed estimator is proposed for accurate crowd-sensing trajectories data pre-processing under different handheld modes. The Bi-LSTM network is further applied for floor identification, and the indoor network matching algorithm is adopted for the generation of fingerprinting database without pain. In the online phase, an error ellipse-assisted particle filter is proposed for the intelligent integration of inertial odometry, crowdsourced Wi-Fi fingerprinting, and indoor map information. The experimental results prove that the proposed ML-CTEF realizes autonomous and precise 3D indoor localization performance under complex and large-scale indoor environments; the estimated average positioning error is within 1.01 m in a multi-floor contained indoor building.

Object recognition, as one of the most fundamental and challenging problems in high-resolution remote sensing image interpretation, has received increasing attention in recent years. However, most conventional object recognition pipelines aim to recognize instances with bounding boxes in a supervised learning strategy, which require intensive and manual labor for instance annotation creation. In this paper, we propose a weakly supervised learning method to alleviate this problem. The core idea of our method is to recognize multiple objects in an image using only image-level semantic labels and indicate the recognized objects with location points instead of box extent. Specifically, a deep convolutional neural network is first trained to perform semantic scene classification, of which the result is employed for the categorical determination of objects in an image. Then, by back-propagating the categorical feature from the fully connected layer to the deep convolutional layer, the categorical and spatial information of an image are combined to obtain an object discriminative localization map, which can effectively indicate the salient regions of objects. Next, a dynamic updating method of local response extremum is proposed to further determine the locations of objects in an image. Finally, extensive experiments are conducted to localize aircraft and oiltanks in remote sensing images based on different convolutional neural networks. Experimental results show that the proposed method outperforms the-state-of-the-art methods, achieving the precision, recall, and F1-score at 94.50%, 88.79%, and 91.56% for aircraft localization and 89.12%, 83.04%, and 85.97% for oiltank localization, respectively. We hope that our work could serve as a basic reference for remote sensing object localization via a weakly supervised strategy and provide new opportunities for further research.

Object detection is a challenging task in aerial images, where many objects have large aspect ratios and are densely arranged. Most anchor-based rotating detectors assign anchors for ground-truth objects by a fixed restriction of the rotation Intersection-over-Unit (IoU) between anchors and objects, which directly follow horizontal detectors. Due to many directional objects with a large aspect ratio, the object-anchor IoU is heavily influenced by the angle, which may cause few anchors assigned for some ground-truth objects. In this study, we propose an anchor selection method based on sample balance assigning anchors adaptively, which we name the Self-Adaptive Anchor Selection (A2S-Det) method. For each ground-truth object, A2S-Det selects a set of candidate anchors by horizontal IoU. Then, an adaptive threshold module is adopted on the set of candidate anchors, which calculates a boundary of these candidate anchors aiming to keep a balance between positive and negative anchors. In addition, we propose a coordinate regression of relative reference (CR3) module to precisely regress the rotating bounding box. We test our method on a public aerial image dataset, and prove better performance than many other one-stage detectors and two-stage detectors, achieving the mAP of 70.64. An efficiency anchor matching method helps the detector achieve better performance for objects with large aspect ratios.