Abstract A new method for automatic counting of etched fission tracks in minerals is developed and recently published in Geochronology (see Nachtergaele and De Grave, 2021). Artificial intelligence techniques such as deep neural networks and computer vision were trained to detect fission surface semi-tracks on images. The deep neural networks can be used in an open source computer program for semi-automated fission track dating called “AI-Track-tive”. Our custom-trained deep neural networks use YOLOv3 object detection algorithm, which is currently one of the most powerful and fastest object recognition algorithms. Two Deep Neural Networks were trained for both apatite and mica using our training dataset with images from the available microscope. The developed program successfully finds most of the fission tracks in the microscope images, however, the user still needs to supervise the automatic counting. The presented deep neural networks have high precision for apatite (97%) and mica (98%). Recall values are lower for apatite (86%) than for mica (91%). These high values have been obtained on images using the same microscope that provided the training images. The application can be used online on the web page https://ai-track-tive.ugent.be or after download as an offline application for Windows. The online application can be used to analyse captured images and does not require installation or download. The offline application can be used for both live track recognition on live microscopy images and captured images of apatite or mica. AI-Track-tive is written in Python and can be downloaded on https://github.com/SimonNachtergaele.