A context-based object classifying model is applied to a set of object location representations (12, 14), derived from an object detection applied to a frame (10) of a video stream, to obtain a context-adapted classification probability for each object location representation (12, 14). Each object location representation (12, 14) defines a region of the frame (10) and each context-adapted classification probability represents a likelihood that the region comprises an object (11, 13). The model is generated based on object location representations from previous frames of the video stream. It is determined whether the region defined by the object location representation (12, 14) comprises an object (11, 13) based on the context-adapted classification probability and a detection probability. The detection probability is derived from the object detection and represents a likelihood that the region defined by the object location representation (12, 14) comprises an object (11, 13).