Computer vision plays a key role in vehicle technology, some examples are advanced driver assistance systems (ADAS), exploratory and service robotics, unmanned aerial vehicles and underwater robots. In addition to traditional applications such as lane departure warning, traffic object recognition, visual odometry or trajectory planning, new challenges are arising: learning and evaluation with reduced groundtruth/testing data, on-board calibration for multi-cameras, SLAM in natural scenarios, etc. The goal of the 4th CVVT:E2M workshop, to be hosted in ICCV 2013 in Sydney (Australia), is to get together researchers in computer vision for vehicular technologies, in order to and promote development and spreading of new ideas and results across the aforementioned fields.