Blindness affects millions of people worldwide, leading to difficulties in daily travel and a loss of independence due to a lack of spatial information. This article proposes a new navigation aid to help people with severe blindness reach their destination. Blind people are guided by a short 3D spatialised sound that indicates the target point to follow. This sound is combined with other sonified information on potential obstacles in the vicinity. The proposed system is based on inertial sensors, GPS data, and the cartographic knowledge of pedestrian paths to define the trajectory. In addition, visual clues are used to refine the trajectory with ground floor information and obstacle information using a camera to provide 3D spatial information. The proposed method is based on a deep learning approach. The different neural networks used in this approach are evaluated on datasets that regroup navigations from pedestrians’ point-of-view. This method achieves low latency and real-time processing without relying on remote connections, instead using a low-power embedded GPU target and a multithreaded approach for video processing, sound generation, and acquisition. This system could significantly improve the quality of life and autonomy of blind people, allowing them to reliably and efficiently navigate in their environment.
The aim of this trial was to study the influence of feed form on the performance, gizzard development and carcass traits of growing geese. Between 42 and 98 days of age, 360 geese (type Maxipalm®) were fed a diet containing 500 g sorghum/kg (nitrogen-corrected apparent metabolizable energy 12.6 MJ/kg, 15.1 g/kg CP). Birds were divided into three groups differing in feed form: complete pellets (Control group, n = 120); a coarse-ground meal (CG group, n = 120); or a mixture containing protein-rich pellets and sorghum whole grains (M group, n = 120). Feed intake per pen (40 birds/pen) was measured weekly between 42 and 98 days of age, and individual live weight (LW) was measured every 2 weeks. At 84 and 98 days of age, 12 birds were slaughtered in each group to measure the gizzard development and body traits. Irrespective of the goose sex, LW at 98 days was lower for the CG group than for the Control group (5555 v. 5888 g, P < 0.05 for males and 5039 v. 5215 g, P < 0.05 for females). The feed intake over the entire period was 5.5% higher in the M group (P < 0.05) than in the Control and CG groups but the feed conversion ratio (6.91, P > 0.05) was similar in the three groups. The gizzard development (as % of LW) was higher in birds of the CG group than those of the Control and M groups at 84 days of age (+13.98% and +13.51%, respectively; P < 0.05) but was similar in all three groups at 98 days of age (4.01%, P > 0.05). The relative liver development was lower in the birds of the CG group than those of the other two groups at 84 and 98 days of age (−20%, P < 0.001 and −10%, P < 0.05, respectively). The other body traits were similar in the three groups at both 84 and 98 days of age. The present results suggest that a simplified diet presented in the form of a mixture of sorghum whole grains and protein-rich pellets did not reduce the performance of growing geese.
12 September 2018 in Semantic Web: – Interoperability, Usability, Applicability
The contextual information in the built environment is highly heterogeneous, it goes from static information (e.g. , information about the building structure) to dynamic information (e.g. , user’s space–time information, sensors detections and events