The application of home service robots is the future development trend of mobile robots. To make the mobile robot perceive the family living environment and serve all kinds of people, based on collecting images and segmenting them into data sets, a semantic segmentation method for the family living environment is proposed. The photographed images of the research objects (bed and stroller) constitute the image dataset which is split into training and test datasets. Two semantic segmentation algorithms, FCN and SegNet, are utilized to learn the training set, and the performance of each semantic segmentation algorithm is compared and evaluated on the test set. Experimental results show that the accuracy of the two semantic segmentation algorithms for strollers is higher than that for beds. Among them, the AP and the MIoU of the FCN algorithm for the stroller are 95.39%, and 91.08% respectively whereas the SegNet algorithm is 88.88%, and 81.34% respectively. The FCN algorithm shown better performance compared to the SegNet algorithm and it can be applied in our daily life. © 2020 IEEE.

Presently, there exist few 3D imaging methods that can simultaneously acquire both 3-dimensional spatial information and material information of the environment by a single shot and single camera. Moreover, they cannot meet the need for high efficiency with low energy consumption and compact shape at the same time. This paper proposes a multispectral 3D sensing system for single frame monocular equipment that performs synchronal acquisition of both visual image and depth information of the scene. The system uses the snapshot narrow-band multispectral longitudinal dispersion enhanced optical imaging system to obtain multiple spectral band images with different defocusing degrees and carries the depth recovery by comparing and analyzing the defocusing amount of each spectral band and the differential signal formed between spectral bands. This system provides a compact real-time 3D vision system with low energy consumption, high robustness, and strong endurance. It is suitable for unmanned aerial vehicles, aerospace, robots, and other automobiles equipment to navigate in both indoor and outdoor non-structured environments. © 2020 IEEE.

Mercury ion (Hg²⁺) is one of the common pollutants which exists in the natural environment far and wide. The detection of Hg²⁺ usually requires large laboratory equipment, which limits their field applications. Here, a miniaturised optical fibre sensor based on quantum dots (QDs) for detection of Hg²⁺ is developed. The sensor is based on the principle of fluorescence quenching caused by Hg²⁺ and evanescent wave sensing. It is an all-fibre sensor which composed of an optical fibre probe module, an optical module and a signal acquisition module. Through miniaturisation design of optical system and the structure of the sensor, the sensor is reduced to the volume of 120 × 120 × 100 mm. The experimental results show that in the miniaturised sensor both has high sensitivity and fast response speed. Meanwhile, the ion anti-interference experiment shows that the sensor has good selectivity for Hg²⁺ detection. In general, the proposed sensor has significant potential in the field of biochemistry, environmental monitoring, and food safety.
© 2019 Institution of Engineering and Technology. All rights reserved.

Mercury ion (Hg²⁺) is one of the common pollutants which exists in the natural environment far and wide. The detection of Hg²⁺ usually requires large laboratory equipment, which limits their field applications. Here, a miniaturised optical fibre sensor based on quantum dots (QDs) for detection of Hg²⁺ is developed. The sensor is based on the principle of fluorescence quenching caused by Hg²⁺ and evanescent wave sensing. It is an all-fibre sensor which composed of an optical fibre probe module, an optical module and a signal acquisition module. Through miniaturisation design of optical system and the structure of the sensor, the sensor is reduced to the volume of 120 × 120 × 100 mm. The experimental results show that in the miniaturised sensor both has high sensitivity and fast response speed. Meanwhile, the ion anti-interference experiment shows that the sensor has good selectivity for Hg²⁺ detection. In general, the proposed sensor has significant potential in the field of biochemistry, environmental monitoring, and food safety.
© 2019 Institution of Engineering and Technology. All rights reserved.