Extended target tracking utilizing machine-learning software -- with applications to animal classification
This work addresses robust object tracking and classification in wildlife monitoring, but it is incremental as it builds on existing filtering methods with a specific extension.
The paper tackles the problem of detecting and tracking objects in image sequences by extending a filtering framework to incorporate class information from previous frames, which improves classification robustness, as demonstrated on camera trap images of four Swedish carnivores.
This paper considers the problem of detecting and tracking objects in a sequence of images. The problem is formulated in a filtering framework, using the output of object-detection algorithms as measurements. An extension to the filtering formulation is proposed that incorporates class information from the previous frame to robustify the classification, even if the object-detection algorithm outputs an incorrect prediction. Further, the properties of the object-detection algorithm are exploited to quantify the uncertainty of the bounding box detection in each frame. The complete filtering method is evaluated on camera trap images of the four large Swedish carnivores, bear, lynx, wolf, and wolverine. The experiments show that the class tracking formulation leads to a more robust classification.