Pollen Bearing Honey Bee Detection in Hive Entrance Video Recorded by Remote Embedded System for Pollination Monitoring

Abstract

ABSTRACT:Honey bees have crucial role in pollination across the world. This paper presents a simple, non-invasive, system for pollen bearing honey bee detection in surveillance video obtained at the entrance of a hive. The proposed system can be used as a part of a more complex system for tracking and counting of honey bees with remote pollination monitoring as a final goal. The proposed method is executed in real time on embedded systems co-located with a hive. Background subtraction, color segmentation and morphology methods are used for segmentation of honey bees. Classification in two classes, pollen bearing honey bees and honey bees that do not have pollen load, is performed using nearest mean classifier, with a simple descriptor consisting of color variance and eccentricity features. On in-house data set we achieved correct classification rate of 88.7% with 50 training images per class. We show that the obtained classification results are not far behind from the results of state-of-the-art image classification methods. That favors the proposed method, particularly having in mind that real time video transmission to remote high performance computing workstation is still an issue, and transfer of obtained parameters of pollination process is much easier.

Application of Digital Particle Image Velocimetry to Insect Motion: Measurement of Incoming, Outgoing, and Lateral Honeybee Traffic

“…Babic et al [20] proposed a system for pollen bearing honeybee detection in surveillance videos obtained at the entrance of a hive. The system's hardware includes a specially designed wooden box with a raspberry pi camera module inside.…”

An Approximate GEMM Unit for Energy-Efficient Object Detection

“…Despite recent advances, the detection of small, fast-moving objects, such as honeybees, where processing speed plays a critical role, remains a challenging task. In [ 7 , 8 , 9 , 10 , 11 ], several systems for identifying honeybees and pollen loads, as well as monitoring the health conditions in a beehive were proposed. Babic et al [ 7 ] proposed a Raspberry Pi-based system for the detection of pollen-bearing bees.…”

Polen Taşıyan Bal Arılarının MobileNetV2 Mimarisi ile Sınıflandırılması

“…Aynı zamanda polenler insanoğlu için oldukça zengin protein ve vitamin kaynağı olduğundan, arı çiftçileri tarafından kovan girişine kurulan tuzaklar yardımıyla toplanmaktadır (Ankara Valiliği Gıda Tarım ve Hayvancılık İl Müdürlüğü, 2015;Bozkurt, 2020). Bu nedenlerden dolayı, kovana giren arılardan polen taşıyanların sayısı, yoğunluğu gibi nicelikler, arı çiftçilerinin hem kovanların genel sağlık durumu hem de kovanın rekoltesi hakkında yorum yapabilmelerine imkân sağlamaktadır (Babic et al, 2016).…”

“…Babic vd. (Babic et al, 2016) 2016 yılında gerçekleştirdikleri çalışmada Rasperry Pi kartına takılan bir kamera aracılığıyla görüntüler almışlardır. Oluşturdukları veri setinde yer alan arıların segmentasyonu sürecinde Gauss Karışım Modeli modeli kullanan araştırmacılar, çıkarımını yaptıkları özellikleri en yakın ortalama algoritması ile sınıflandırmışlardır.…”