Minkowski compactness measure

Abstract

Abstract-Many compactness measures are available in the literature. In this paper we present a generalised compactness measure Cq(S) which unifies previously existing definitions of compactness. The new measure is based on Minkowski distances and incorporates a parameter q which modifies the behaviour of the compactness measure. Different shapes are considered to be most compact depending on the value of q: for q = 2, the most compact shape in 2D (3D) is a circle (a sphere); for q → ∞, the most compact shape is a square (a cube); and for q = 1, the most compact shape is a square (a octahedron).For a given shape S, measure Cq(S) can be understood as a function of q and as such it is possible to calculate a spectum of Cq(S) for a range of q. This produces a particular compactness signature for the shape S, which provides additional shape information.The experiments section of this paper provides illustrative examples where measure Cq(S) is applied to various shapes and describes how measure and its spectrum can be used for image processing applications.

Cow detection and tracking system utilizing multi-feature tracking algorithm

“…In most previous research works, multiple object detection and tracking (MODT) approach for cattle farms have been developed for various objectives [7][8][9]28 . For example, various MOT methods have been developed for recording and analyzing various events preceding calving, assisting specific cows when calving, and monitoring daily routines and health conditions of cattle 10,29 . In our proposed work, we developed a multiple cow detection and tracking system using a tracking-by-detection approach.…”

“…We check the active status (Status p temp ) of the p temp in every frame. If the newly detected object is visible for ( Age temp /2 ), we calculated location distance, L dist , the average color distance, C dist,avg , average texture distance, T dist,avg , and average probability distance P dist,avg between p missed and p temp as expressed in (10).…”

“…Valuable information for assessing cattle health can be obtained by monitoring daily activities such as time spent sitting or in a restless state, the frequency of drinking, feeding, or rumination, as well as the posture of cows when sitting. To achieve the objectives of a health monitoring system, some cattle farms use biosensors to retrieve biometric data related to specific diseases, preventing outbreaks [6][7][8][9][10] . As previously explained, accurately detecting, and tracking cows is the starting point in building a robust cow monitoring system.…”

Convolutional neural network‐based cow interaction watchdog

“…Most previous work on detecting cows by using video cameras has been focused on monitoring areas where the orientation of the cows was known due to physical limitations imposed by the surroundings. Two examples of this are the Viola-Jones-based detector of Arcidiacono et al [8] for detecting cows at the feed barrier and the work of Martinez-Ortiz et al [9] to detect and track cow heads in narrow entrance corridors. There are also approaches that rely on more advanced sensors, such as Abdul Jabbar et al [10], that use a depth camera.…”