Live cell imaging is a key approach in cell biology to study dynamic cellular mechanisms and cell fate in physiological conditions and upon genetic or chemical alterations. Video recording allows the biologist to observe the dynamic behavior of cells and to quantify useful information, such as the number, size, and shape of cells and their dynamic changes across time. Consequently, time-lapse microscopy imaging is a relevant approach for biomedical applications. The task of detecting and tracking multiple moving objects in a video presents several issues, as cells change their morphology over time and can partially overlap, and cell division leads to new cells. Therefore, the application of these image analyses to extended datasets requires automated approaches based on computer vision and machine/deep learning approaches to define complex phenotypic profiles. Here, we provide an overview of methods, software, and data for the automatic analysis of live cell imaging, focusing on label-free imaging, that ensures that native cell behavior remains uninfluenced by the recording process.