Posted road speed limits contribute to the safety of driving, yet when certain driving conditions occur, such as rain, snow or fog, they become less meaningful to the drivers. To overcome this limitation, there is a need for adaptive speed limits system to improve road safety under varying driving conditions. In that vein, a visibility range estimation method for real-time adaptive speed limits control in intelligent transportation systems using three algorithms, namely, the improved dark channel prior (DCP) and grayscale image entropy (GIE), and the support vector machine (SVM) classifier is proposed in this thesis. The information required to specify the speed limit is captured via a road side unit that collects environmental data and captures road images, which are then analyzed locally or on the cloud. The proposed system results exhibit 15.13% accuracy enhancement over the other considered techniques such as the conventional DCP and GIE.