Computing a rodent’s diary

Abstract

Rodent monitoring in biomedical laboratories is a time consuming and tedious task. Several automatic solutions that rely on different types of sensors have been proposed. Computer vision provides a significantly more universal and less intrusive solution. In this article we propose a new method to detect and classify three behaviors in rodents: exploring, rearing, and static. The method uses motion history images and a multiple classifier system to detect the three behaviors under typical laboratory conditions. It is independent of the color of the rodent and of the background. The method performs equally well on short and long video sequences, achieving a success rate of 87 %.

Pharmaco‐electroencephalographic responses in the rat differ between active and inactive locomotor states

“…This method favouring precision ensured that subsequent state‐specific analyses of LFPs/ECoGs were reliable. Precision is rarely reported (see Table ) in other publications on methods for classifying rodent behaviour (Belic et al., ; Chanchanachitkul, Nanthiyanuragsa, & Rodamporn, ; Crispim‐Junior, de Azevedo, & Marino‐Neto, ; Dollar et al., ; Farah et al., ; Jhuang et al., ; Kabra, Robie, Rivera‐Alba, Branson, & Branson, ; Steele et al., ; van Dam et al., ; van den Boom, Pavlidi, Wolf, Mooij, & Willuhn, ; Wang, Mirbozorgi, & Ghovanloo, ). Previously reported precisions for the detection of rearing, resting, and walking behaviours have been 58%, 70%, and 70%, respectively, for the method proposed by Zarringhalam et al.…”

“…Later relevant studies in rats have not explicitly reported precision, and their chance accuracy is higher than ours, as we intentionally leave some data unassigned. Video‐based systems have achieved accuracies of 65%–80% for classification of 11 behaviours (van Dam et al., ) and 87% (“success rate”) for classification of “exploring,” “rearing”, and “static” states (Farah et al., ). An accuracy of 89% has been obtained for kinect‐based classification of five behaviours in dark conditions (Wang et al., ), and 87%–91% for classification of active and resting behaviours based on LFP (Belic et al., ).…”

“…In the awake state, drug‐effects on LFP/ECoG evaluated specifically within a behavioural state have most often been obtained through manual behavioural scoring (Coenen & van Luijtelaar, ; Leccese, Marquis, Mattia, & Moreton, ; Sławińska & Kasicki, ; van Lier, Drinkenburg, van Eeten, & Coenen, ), which is tedious and time‐consuming work possibly prone to varying detection‐precision. Although technical solutions to track locomotor activity in rodents have been used for long (Schmitt & Hiemke, ), and behavioural‐state classification methods have been developed and validated against manual scoring (Belic, Halje, Richter, Petersson, & Kotaleski, ; Dollar, Rabaud, Garrison, & Belongie, ; Farah, Langlois, & Bilodeau, ; Jhuang et al., ; Steele, Jackson, King, & Lindquist, ; van Dam et al., ; Zarringhalam et al., ) we have found that studies, analysing LFP/ECoG in specific automatically detected states, use methods unvalidated against manual scoring (Ahnaou, Huysmans, Biermans, Manyakov, & Drinkenburg, ; Ahnaou, Huysmans, van de Casteele, et al., ; Kealy, Commins, & Lowry, ; Lee et al., ). How well behaviour is classified inevitably determines the reliability of subsequent state‐specific analyses, thus employing methods with high classification performance and time‐resolution is important.…”

Captive Animal Behavior Study by Video Analysis

“…To objectively measure the relevant behaviors, many automated video monitoring and motion investigation techniques have been studied. There are proposals where the specificity of the scene imposes very particular tracking and trajectory analysis algorithms [ 1 , 2 , 3 , 4 , 5 ]. A recent review of the currently available open-source tools for animal behavioral video analysis is presented in [ 6 ].…”

“…Analysis of the synthesized trajectory identified three rodent behaviors (exploring, rearing, and freezing). An improved version of motion analysis was later presented in [ 3 ]. Motion History Images and a Multiple Classifier System were used to recognize the three comportments.…”