Search

This paper describes a novel visible light positioning (VLP) system called RefRec+ allowing to estimate the six degree-of-freedom (6DoF) of a smartphone. In most existing VLP systems, their front camera faces multiple light sources installed at different places on a ceiling to detect their direct signals. To overcome the problem of the limited field of views that causes failure to capture required numbers of light sources for positioning and that of the high computational complexity because of image processing to a large-sized pixel data, RefRec+ captures indirect lights from the light sources reflected via a floor. RefRec+ estimates the 2-D position of a point of interest (POI) by calculating the received signal strength of individual light sources using the floor image captured by the camera. Using 2-D positions of multiple POIs and the angle of arrival method, RefRec+ obtains the 6DoF of the smartphone. Several experiments to confirm the performance of RefRec+ were conducted. Experimental results in a room measuring 4.0 m x 4.0 m using nine POIs each of which consists of 32 x 32 pixels in a captured image showed that the absolute errors at the 90th percentile for the 3-D coordinates were 0.2073 m, 0.1713 m, and 0.002464 m along the X, Y, and Z axes, respectively, and for the pitch, roll, and yaw angles were 5.78, 5.69 and 3.96 degrees, respectively.

In this paper, we describe a visible-light positioning system that uses the ambient-light sensor assembly in a smartphone as a receiver for illumination signals from LED-based room lighting. After correcting for missing or inconsistently sampled data captured by the receiver, we can identify the source LEDs contributing to the received signal via Fourier analysis of its frequency distribution. Localization of the smartphone is then achieved by trilateration of the distances to the various LEDs, which are calculated from the received signal strength for each LED. Experiments using multiple LEDs were conducted to evaluate the signal reception and positioning performance of the system. We found that multiple LEDs modulated at frequencies of over 70 Hz could be correctly identified from the received signal pattern. The 90th-percentile 2D positioning errors using low frequency signals (3.951-7.902 Hz) were less than 0.21 meter for a room illuminated by four LEDs arranged in a 1-m square on the ceiling at 2.22 meters height, where the smartphone was placed parallel on the floor from 1.4 meters height. Those using high frequency signals (111.619-114.582 Hz) in the same room setting showed 50th-percentile 2D position errors of less than 0.44 meter. The position calculation was offline and not implemented on real time. Potential applications and limitations of the proposed method are discussed.

This paper describes a novel visible light positioning (VLP) system called RefRec+ allowing to estimate the six degree-of-freedom (6DoF) of a smartphone. In most existing VLP systems, their front camera faces multiple light sources installed at different places on a ceiling to detect their direct signals. To overcome the problem of the limited field of views that causes failure to capture required numbers of light sources for positioning and that of the high computational complexity because of image processing to a large-sized pixel data, RefRec+ captures indirect lights from the light sources reflected via a floor. RefRec+ estimates the 2-D position of a point of interest (POI) by calculating the received signal strength of individual light sources using the floor image captured by the camera. Using 2-D positions of multiple POIs and the angle of arrival method, RefRec+ obtains the 6DoF of the smartphone. Several experiments to confirm the performance of RefRec+ were conducted. Experimental results in a room measuring 4.0 m x 4.0 m using nine POIs each of which consists of 32 x 32 pixels in a captured image showed that the absolute errors at the 90th percentile for the 3-D coordinates were 0.2073 m, 0.1713 m, and 0.002464 m along the X, Y, and Z axes, respectively, and for the pitch, roll, and yaw angles were 5.78, 5.69 and 3.96 degrees, respectively.

Most visible light communication (VLC) technologies use a light emitting diode (LED) as a data transmitter and a photodiode as a receiver. In this paper, we alternatively focus on the use of an image sensor or camera as a receiver due to its wide availability. However, the successful use of an image sensor mainly depends on the efficiency of the encoder-decoder and the modulation scheme. Thus, this paper proposes a novel modulation scheme based on a square wave signal called a square wave quadrature amplitude modulation (SW-QAM) method. This method can accommodate different camera settings and overcome the problem of LED flicker that is generally sensed by human eyes when the LED frequency is low. At the transmitter side, multiple LEDs can be used to increase the transmission bit rate, while, at the receiver side, a Wiener filter is used as a complementary technique to SW-QAM for solving the light interference phenomenon due to the closeness of one LED to another. Our experimental results show that the proposed SW-QAM scheme can decode symbols very well either the for close or far communication distances, dark or bright lighting conditions, and single or multiple LED points.

We have proposed a square wave quadrature amplitude modulation (SW-QAM) scheme for visible light communication (VLC) using an image sensor in our previous work. Here, we propose a robust and unified system by using a neural decoding method. This method offers essential SW-QAM decoding capabilities, such as LED localization, light interference elimination, and unknown parameter estimation, bundled into a single neural network model. This work makes use of a convolutional neural network (CNN) that has a capability in automatic learning of unknown parameters, especially when it deals with images as an input. The neural decoding method can provide good solutions for two difficult conditions that are not covered by our previous SW-QAM scheme: unfixed LED positions and multiple point spread functions (PSFs) of multiple LEDs. Responding to the above solutions, three recent CNN architectures-VGG, ResNet, and DenseNet-are modified to suit our scheme and other two small CNN architectures-VGG-like and MiniDenseNet-are proposed for low computing devices. Our experimental results show that the proposed neural decoding method performs better in terms of error rate than the theoretical decoding, an SW-QAM decoder with a Wiener filter, in different scenarios. Furthermore, we experiment on the problem of moving camera, i.e., the unfixed position of LED points. For this case, a spatial transformer network (STN) layer is added to the neural decoding method for solving the moving camera problem, and the method with the new layer achieves a remarkable result.

In this paper, we introduce a self-constructive Normalized Gaussian Network (NGnet) for online learning tasks. In online tasks, data samples are received sequentially, and domain knowledge is often limited. Then, we need to employ learning methods to the NGnet that possess robust performance and dynamically select an accurate model size. We revise a previously proposed localized forgetting approach for the NGnet and adapt some unit manipulation mechanisms to it for dynamic model selection. The mechanisms are improved for more robustness in negative interference prone environments, and a new merge manipulation is considered to deal with model redundancies. The effectiveness of the proposed method is compared with the previous localized forgetting approach and an established learning method for the NGnet. Several experiments are conducted for a function approximation and chaotic time series forecasting task. The proposed approach possesses robust and favorable performance in different learning situations over all testbeds.