Show simple item record

dc.rights.licenseCC-BY-NC-ND
dc.contributor.advisorSalah, Albert
dc.contributor.authorKoetsier, Lisanne
dc.date.accessioned2024-08-19T23:01:10Z
dc.date.available2024-08-19T23:01:10Z
dc.date.issued2024
dc.identifier.urihttps://studenttheses.uu.nl/handle/20.500.12932/47308
dc.description.abstractStudying dog behavior is a crucial aspect in determining their welfare since their behavior cues reflect their mental state. Studying behaviors in dogs can aid veterinarians in estimating their pain levels. Especially dogs experiencing chronic pain are masters at masking their pain signals. Deep learning models might be able to pick up the pain signals that even experts do not immediately notice. Our starting point is a two-stream network encompassing a ConvLSTM stream for RGB frames and an LSTM stream for processing keypoints to classify pain. We propose adding a third stream that encapsulates an ethogram, representing the dogs' behaviors in the corresponding input frames to improve the baseline two-stream pain estimation model. We established a method that uses the Multi-modal Semantic Query Network (MSQNet) to generate behavior labels for unlabeled data to deal with the problem of annotating an abundance of videos, which is a labor-intensive and time-consuming process. We processed the ethograms using two different methods: a simple linear layer and a random forest classifier, respectively. Analyzing the performance of these methods showed us that the former performed better than the latter, possibly due to the limited amount of training samples available. Additionally, explainability is a crucial aspect of pain detection in dogs, since we want to know why the dogs appear to be in pain. We tested several methods to aid explainability, including saliency heatmaps, Shapley values, Naive Bayes probabilities, confidence scores, and a decision tree. From the explainability measures, we can conclude that the models tend to classify dogs with higher activity into the ``no pain" class, and dogs with low activity into the ``pain" class.
dc.description.sponsorshipUtrecht University
dc.language.isoEN
dc.subjectStudying dog behavior is key to assessing their welfare, as behaviors reflect mental states and pain levels. Chronic pain in dogs is hard to detect, but deep learning models might identify subtle signals. A two-stream network (ConvLSTM for RGB frames, LSTM for keypoints) was enhanced with a third stream using ethograms to classify pain. Ethogram processing via a linear layer outperformed a random forest classifier. Explainability tests revealed that low activity often led to pain classification.
dc.titleAutomated Behavior Estimation for Pain Detection in Dogs with Computer Vision
dc.type.contentMaster Thesis
dc.rights.accessrightsOpen Access
dc.subject.keywordsDog pain; behavior detection; action recognition; computer vision; MSQNet; CLIP; pain detection
dc.subject.courseuuArtificial Intelligence
dc.thesis.id37051


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record