This work proposes a novel framework for visual tracking based on the integration of an iterative particle filter, a deep convolutional neural network, and a correlation filter.
The multiple hypothesis tracking algorithm then keeps track of the temporal identifiers of the targets based on the cluster centroids.
The feature vectors and the constraints graphs are then provided to the kmeans clustering algorithm to separate the corresponding data points in the latent space.
Experiments using multiple modern semantic segmentation networks and benchmark datasets demonstrate the effectiveness of our approach for the refinement of segmentation predictions at different levels of coarseness, as well as the suitability of the variance estimates obtained in the Monte Carlo iterations as uncertainty measures that are highly correlated with segmentation accuracy.
Effective assisted living environments must be able to perform inferences on how their occupants interact with one another as well as with surrounding objects.
Camera network and multi-camera calibration for external parameters is a necessary step for a variety of contexts in computer vision and robotics, ranging from three-dimensional reconstruction to human activity tracking.
Large-scale annotation of image segmentation datasets is often prohibitively expensive, as it usually requires a huge number of worker hours to obtain high-quality results.
The re-labeling approach employs a region growing mechanism that aggregates these pixels to neighboring areas with high confidence scores and similar appearance.
The autonomous measurement of tree traits, such as branching structure, branch diameters, branch lengths, and branch angles, is required for tasks such as robotic pruning of trees as well as structural phenotyping.
We consider the problem of extracting curve skeletons of three-dimensional, elongated objects given a noisy surface, which has applications in agricultural contexts such as extracting the branching structure of plants.