Automated Driving Systems (ADS) and Advanced Driving Assistance Systems (ADAS) are widely investigated for developing safe and intelligent transportation systems. A common module in both systems is road objects monitoring, in which the semantic segmentation for road scene understanding has encountered lots of challenges. Due to the rapid evolution in technologies applied in vision-based systems in many fields, diverse techniques and algorithms have emerged to tackle such limitations, as invariant-illumination conditions, shadows, false positives, misdetections, weather conditions, real time processing and occlusions. A comparative study is conducted in this paper for vehicle detection and tracking methods applied on images and streams produced from monocular cameras and sensors in ADAS and ADS in terms of the aforementioned problems, the used dataset, along with the extracted features and the associated evaluation criteria. The study deduces the limitations of the current state-of-art techniques in such particular systems and highlights the main directions that can be ado ted for future research and investigations.