I have yet to see any problem, however complicated, which, when you looked
at it the right way, did not become still more complicated.
— Paul Alderson (1926-…) in “New Scientist”, 25 September 1969, 638
Visual tracking performance has long been limited by the lack of better appearance models. These models fail either where they tend to change rapidly, like in motion-based tracking, or where accurate information of the object may not be available, like in color camouflage (where background and foreground colors are similar). This paper proposes a robust, adaptive appearance model which works accurately in situations of color camouflage, even in the presence of complex natural objects. The proposed model includes depth as an additional feature in a hierarchical modular neural framework for online object tracking. The model adapts to the confusing appearance by identifying the stable property of depth between the target and the surrounding object(s). The depth complements the existing RGB features in scenarios when RGB features fail to adapt, hence becoming unstable over a long duration of time. The parameters of the model are learned efficiently in the Deep network, which consists of three modules:(1) The spatial attention layer, which discards the majority of the background by selecting a region containing the object of interest; (2) the appearance attention layer, which extracts appearance and spatial information about the tracked object; and (3) the state estimation layer, which enables the framework to predict future object appearance and location. Three different models were trained and tested to analyze the effect of depth along with RGB information. Also, a model is proposed to utilize only depth as a standalone input for tracking purposes. The proposed models were also evaluated in real-time using KinectV2 and showed very promising results. The results of our proposed network structures and their comparison with the state-of-the-art RGB tracking model demonstrate that adding depth significantly improves the accuracy of tracking in a more challenging environment (i.e., cluttered and camouflaged environments). Furthermore, the results of depth-based models showed that depth data can provide enough information for accurate tracking, even without RGB information.
Over years correlation filter-based trackers have proved their worth with their increased efficiency and increased computation speed. Kernelized Correlation Filter (KCF) was one such attempt which, by using kernel trick, achieved compelling result as compared to traditional correlation filter-based trackers. In this paper, our goal is to analyze this tracker to observe its strengths and weaknesses in detail. We use Kinect RGB camera for our experimental analysis and report our findings. The analysis showed that KCF is not only computationally very fast, it is time-invariant and very robust to speed and vertical motions. However, it is not very robust to illumination variations, scale and color.
In this book chapter, we propose the design and development of a low-cost IoT framework formonitoring landslide is discussed. This framework involved the use of MEMS-based sensors for monitoring landslides at the lab scale. The proposed frame-work can monitor soil moisture and movement and generate alerts based onpredefined thresholds.
Changes in the Earth’s climate are likely to increase natural hazards such as drought, floods, earthquakes,landslides, etc. The present study focusing on to early warning systems (EWS) of landslides, major issues in Himalayan regionwithout prominence to deforestation, encroachments and un-engineered cutting of slopes and reforming for infrastructuralpurposes. EWS can be depicted by conducting a series of flume tests using micro-electro mechanical systems sensors data afterreaching threshold values under controlled laboratory conditions. Based on the threshold value database, an alert will be sentvia SMS