Daily acquisition of large amounts of aerial and satellite images has facilitated subsequent automatic interpretations of these images. One such interpretation is object detection. Despite the great progress made in this domain, the detection of multi-scale objects, especially small objects in high resolution satellite (HRS) images, has not been adequately explored. As a result, the detection performance turns out to be poor. To address this problem, we first propose a unified multi-scale convolutional neural network (CNN) for geospatial object detection in HRS images. It consists of a multi-scale object proposal network and a multi-scale object detection network, both of which share a multi-scale base network. The base network can produce feature maps with different receptive fields to be responsible for objects with different scales. Then, we use the multi-scale object proposal network to generate high quality object proposals from the feature maps. Finally, we use these object proposals with the multi-scale object detection network to train a good object detector. Comprehensive evaluations on a publicly available remote sensing object detection dataset and comparisons with several state-of-the-art approaches demonstrate the effectiveness of the presented method. The proposed method achieves the best mean average precision (mAP) value of 89.6%, runs at 10 frames per second (FPS) on a GTX 1080Ti GPU.

No abstract

No abstract

Robust frequency-hopping spectrum estimation based on sparse bayesian method

Power line detection plays an important role in an automated UAV-based electricity inspection system, which is crucial for real-time motion planning and navigation along power lines. Previous methods which adopt traditional filters and gradients may fail to capture complete power lines due to noisy backgrounds. To overcome this, we develop an accurate power line detection method using convolutional and structured features. Specifically, we first build a convolutional neural network to obtain hierarchical responses from each layer. Simultaneously, the rich feature maps are integrated to produce a fusion output, then we extract the structured information including length, width, orientation and area from the coarsest feature map. Finally, we combine the fusion output with structured information to get a result with clear background. The proposed method fully exploits multiscale and structured prior information to conduct both accurate and efficient detection. In addition, we release two power line datasets due to the scarcity in the public domain. The method is evaluated on the well-annotated power line datasets and achieves competitive performance compared with state-of-the-art methods.

Device-free localization (DFL) based on wireless sensor networks (WSNs) is expected to detect and locate a person without the need for any wireless devices. Radio tomographic imaging (RTI) has attracted wide attention from researchers as an emerging important technology in WSNs. However, there is much room for improvement in localization estimation accuracy. In this paper, we propose a geometry-based elliptical model and adopt the orthogonal matching pursuit (OMP) algorithm. The new elliptical model uses not only line-of-sight information, but also non-line-of-sight information, which divides one ellipse into several areas with different weights. Meanwhile the OMP, which can eliminate extra bright spots in image reconstruction, is used to derive an image estimator. The experimental results demonstrate that the proposed algorithm could improve the accuracy of positioning by up to 23.8% for one person and 33.3% for two persons over some state-of-the-art RTI methods.

No abstract

The future wireless communication is expected to be able to improve the efficiency of spectrum usage. To solve the challenge of spectrum shortage, an innovative opportunistic spectrum access strategy, called cognitive radio (CR) has been proposed. In the concept of CR, secondary users or CR users, are allowed to transmit and receive date by detecting the portions of spectra where/when primary users are inactive provided that secondary transmissions cause no harmful interference to the licensed systems. Conventional orthogonal frequency division multiplexing (OFDM) has also been suggested as a physical layer candidate for CR system. In this paper, another potential candidate for CR, OFDM/offset quadrature amplitude modulation (OQAM) is introduced and compared with cyclic prefix based‐OFDM (CP‐OFDM) and raised cosine windowed‐OFDM (RC‐OFDM) in CR context, in which including spectral efficiency comparison (SEC) for uncoded transmission and coded transmission. SEC is investigated by balancing the tradeoff between the interference level caused by CR user to licensed user (LU) and the throughput of CR user. Simulated results of SEC for different multicarrier systems are interpreted by theoretically analyzing the out‐of‐band radiation of their prototype pulses shaping. Both theoretic analysis and experimental results can show that OFDM/OQAM is a more natural candidate than CP‐OFDM and RC‐OFDM for CR networks application. Copyright © 2008 John Wiley & Sons, Ltd.