In this paper, we address the challenging problem of single-view cross-season place recognition. A new approach is proposed for compact discriminative scene descriptor that helps in coping with changes in appearance in the environment. We focus on a simple effective strategy that uses objects whose appearance remain the same across seasons as valid landmarks. Unlike popular bag-of-words (BoW) scene descriptors that rely on a library of vector quantized visual features, our descriptor is based on a library of raw image data (e.g., visual experience shared by colleague robots, publicly available photo collections from Google StreetView), and directly mines it to identify landmarks (i.e., image patches) that effectively explain an input query/database image. The discovered landmarks are then compactly described by their pose and shape (i.e., library image ID, and bounding boxes) and used as a compact discriminative scene descriptor for the input image. We collected a dataset of single-view images across seasons with annotated ground truth, and evaluated the effectiveness of our scene description framework by comparing its performance to that of previous BoW approaches, and by applying an advanced Naive Bayes Nearest neighbor (NBNN) image-to-class distance measure.

Wireless Body Area Network (WBAN) has drawn considerable attention as a means to gather vital data from on-body sensors. In WBAN, however, a star network topology is mainly supported, connecting a central coordinator to vital sensor nodes put on different positions of a human body, so the links between the coordinator and the sensor nodes are often blocked by parts of the human body when the man takes different postures and motions. Therefore, to support real-time vital data gathering in WBANs, a scheme for mitigating such link blockings is essential. This paper proposes a cooperative scheme for ensuring reliable data transmission in a WBAN. For each sensor node on a human body, the proposed scheme autonomously assigns a sensor node as a cooperator out of other sensor nodes and the cooperator retransmits packets from the sensor node for a coordinator instead of the sensor node when the direct link between them is blocked. After presenting the cooperator selection algorithm, using the Received Signal Strength Indication (RSSI) data obtained from the experiment in an anechoic chamber, the paper evaluates the performance of the proposed scheme in terms of average and worst outage rates.

In a wireless multi-hop network between a source node (S) and a destination node (D), multipath routing in which S redundantly sends the same packets to D through multiple routes at the same time is effective for enhancing the reliability of the wireless data transmission by means of route diversity. However, when applying the multipath routing to a factory where huge robots are moving around, if closer multiple routes are selected, the probability that they are blocked by the robots at the same time becomes higher, so the reliability in terms of packet loss rate cannot be enhanced. This paper proposes a multipath routing method which can select physically distant multiple routes without any knowledge on the locations of nodes. Maximizing the metric composed of "the distance between routes" and "the route quality" by means of scalarization in multi-objective maximization problem, the proposed method can adaptively control the topologies of selected routes between S and D.

Many target localization techniques based on received signal strength indicator (RSSI) assume a prior knowledge of a channel model and its parameters for an area where a target node is localized. This is a limiting factor since an intensive pre- measurement campaign is required to determine the model and its parameters. Basing on channel measurement campaigns in different areas we confirmed that the variation in the RSSIs of the IEEE 802.15.4 signal can be described by a two-layer model. We therefore propose a novel target localization method with no prior knowledge of model parameter values. The method is based on a joint maximum likelihood target localization and channel model parameters estimation. The proposed method was experimentally verified in real environments and the results show that the location estimation accuracy outperforms the accuracy of the conventional method where the values of the channel model parameters are known in advance.

Taking into account requirements of sensor networks, we need fully-distributed and self-organizing control mechanisms which are scalable to the size of a network, robust to failures of sensor nodes, and adaptive to different and dynamically changing topology and changes in wireless communication environment. To accomplish this goal, our research group focuses on behavior of biological systems, which inherently are scalable, adaptive, and robust. In this paper, we first verify the practicality of control mechanisms adopting a reaction diffusion equation, which explains emergence of patterns on the surface of body of fishes and mammals, and then propose two methods for faster pattern generation to save energy consumption. From simulation and practical experiments on a prototype, it was shown that a stable pattern could be generated in a wireless sensor network in several minutes, even when packets were lost for collisions in wireless communication.

Location estimation is one of the most attractive applications in wireless sensor networks. In this paper, we propose a new iterative location estimation method using radio signal strength indicators (RSSIs) not only among target and fixed nodes but also among target nodes. Our computer simulation shows that, if the RSSIs among target nodes are available whose locations are unknown so should be estimated, we can improve the location estimation performance by means of the proposed iterative method

Many applications of wireless sensor networks require to process data cooperatively and to combine information from multiple nodes simultaneously. One of such applications is localisation and tracking where information from many nodes is processed at the same time to accurately estimate targets' positions. However, in case of centralised localisation and tracking applications based on received signal strength indicator (RSSI), where the anchor nodes forward their measured RSSI information to a control centre, the narrow bandwidth of wireless communication link limits the amount of data being forwarded to the control centre. As a result, it cannot receive all the data from the anchor nodes as the number of target nodes increases, and therefore cannot estimate all targets' positions. Thus, we propose a traffic reducing method based on limiting the RSSI information being forwarded and evaluate the proposed method by localising target positions in real environments using maximum likelihood estimation. The results show between 50% and 80% traffic load reduction without severely affecting the estimation accuracy. In addition, the location estimation accuracy is improved at some cases.