A flooding algorithm for extracting drainage networks from unprocessed digital elevation models

Sun

et al. 2020

Preprint

In stock farming, the body size parameters and weight of yaks can reasonably reﬂect the growth and development characteristics, production performance and genetic characteristics of yaks. However, it is diﬃcult for herders to measure the body size and weight of yaks by traditional manual methods. Fortunately, with the development of edge computing, herders can use mobile devices to estimate the yak’s body size and weight. The purpose of this paper is to provide a machine vision-based yak weight estimation method for the edge equipment and establish a yak estimation comprehensive display system based on the user’s use of the edge equipment in order to maximize the convenience of herdsmen’s work. In our method, a set of yak image foreground extraction and measurement point recognition algorithm suitable for edge equipment were developed to obtain yak’s measurement point recognition image, and the ratio between body sizes was transmitted to the cloud server. Then, the body size and weight of yaks were estimated using the data mining method, and the body size estimation data were constantly displayed in the yak estimation comprehensive display system. 25 yaks in different age groups were randomly selected from the herd to perform experiments. The experimental results show that the foreground extraction method can obtain segmentation image with good boundary, and the yak measurement point recognition algorithm has good accuracy and stability. The average error between the estimated values and the actual measured values of body height, oblique length, chest depth, cross height and body weight is 1.95%, 3.11%, 4.91%, 3.35% and 7.79%, respectively. Compared with the traditional manual measurement method, the use of mobile end to estimate the body size and weight of yaks can improve the measurement eﬃciency, facilitate the herdsmen to breed yaks, reduce the stimulation of manual measurement on yaks, and lay a solid foundation for the ﬁne breeding of yaks in Sanjiangyuan region.

Section: Foreground Extraction For Imagesmentioning

confidence: 99%

Body Weight Estimation of Yak Based on Cloud Edge Computing

Sun

et al. 2020

Preprint

“…As for the final image thus generated, please refer to Figure 5. 7In this case, the generated yak boundary image was closed and its central point was set as the starting point to allow filling by feat of a flooding algorithm [26]. As areas where yaks are standing may be eliminated from images obtained in Step 6, color space distance from an edge point of the image obtained based on the flooding algorithm to surrounding pixels was detected.…”

Section: Image Foreground Acquisition Based On Slicmentioning

confidence: 99%

Machine Vision-enabled Yak Weight Estimation on Edge Devices

Sun

et al. 2020

Preprint

In the field of stock farming, body dimensions and weight of a yak may reasonably reveal its growing characters, productivity and genetic characteristics. However, it is arduous for the herdsman to manually measure the body and dimension of yaks. Fortunately, with the development of mobile computing and edge devices, it is preferable and possible for the herdsman to estimate the yaks weight and size with handheld devices (e.g., mobile phones). This paper aims at providing machine visual-based yak body height and weight estimate method for edge devices. In our method, to begin with a foreground image of the yak is extracted; and measuring point identification is carried out to identify measuring points of the yak. Then, a ratio of its body dimensions is acquired. Both body dimensions and weight of the yak are acquired through comparison with relevant data. 25 yaks in different age groups were randomly selected from a herd to perform experiments. As indicated by corresponding experimental results, the foreground extraction approach has the potential to generate split images with good boundaries. As for the measuring point identification method selected for the yak, it features preferable accuracy and stability. For example, estimated values of its standing height, body length, chest depth, hipcross height and body weight, average errors between the measured values and them are proven to be 1.95%, 3.11%, 4.91%,3.35% and 7.79% respectively. By contrast to the traditional measuring approaches, the proposed method may improve measurement efficiency and reduce stimulation caused by manual measurement to the yak.

“…Then, the ridges are extracted through the following three steps: (1) calculate initial ridge cells using flow accumulations estimated by the D8 algorithm of the ArcGIS software, which, after setting zero as the basic condition, returns 1 for ridge cells and 0 otherwise; (2) screen those initial ridge cells with values greater than 0.5 by using a 3 by 3 average window to filter discrete cells; and (3) determine final ridge cells by deleting the cells having negative terrains and the small ridge patches where their eight neighbors all are less than 4. Finally, when extracting the valleys, the flooding algorithm proposed by Rueda et al [35] is adopted to identify the valley cells using the GDAL's C++ library. The flooding algorithm is able to detect watercourses with a width greater than one cell.…”

Section: Calculation Of Terrain Attributesmentioning

confidence: 99%

Effective Identification of Terrain Positions from Gridded DEM Data Using Multimodal Classification Integration

Jiang

Ling

Zhao

et al. 2018

IJGI

Terrain positions are widely used to describe the Earth’s topographic features and play an important role in the studies of landform evolution, soil erosion and hydrological modeling. This work develops a new multimodal classification system with enhanced classification performance by integrating different approaches for terrain position identification. The adopted classification approaches include local terrain attribute (LA)-based and regional terrain attribute (RA)-based, rule-based and supervised, and pixel-based and object-oriented methods. Firstly, a double-level definition scheme is presented for terrain positions. Then, utilizing a hierarchical framework, a multimodal approach is developed by integrating different classification techniques. Finally, an assessment method is established to evaluate the new classification system from different aspects. The experimental results, obtained at a Loess Plateau region in northern China on a 5 m digital elevation model (DEM), show reasonably positional relationship, and larger inter-class and smaller intra-class variances. This indicates that identified terrain positions are consistent with the actual topography from both overall and local perspectives, and have relatively good integrity and rationality. This study demonstrates that the current multimodal classification system, developed by taking advantage of various classification methods, can reflect the geographic meanings and topographic features of terrain positions from different levels.