Cracks on the asphalt pavements are a forewarning of degradation of the structure which calls for a maintenance decision. Pavement condition is assessed using both automated and manual methods. Crack detection equipment integrated with software have been developed to automate pavement distress detection. Technological advances in digital cameras have enhanced photogrammetry such that high-resolution images can now be collected. Manual crack detection relies on the expertise and experience of the specialist. In Malawi, pavement inspectors employ the manual crack detection approach, a method that is subjective, inconsistent, and tedious. This paper seeks to address this weakness by integrating photogrammetry and computer vision in detecting cracks on asphalt pavements. To achieve this, asphalt images were collected in the close-range photogrammetric survey using a ProCam-Manual Control Camera installed in the iPhone 6s. A computer vision (CV) algorithm was developed to automate the crack detection of the captured asphalt images. Results demonstrate that cracks on asphalt pavement can be detected using the proposed computer vision algorithm. Furthermore, the algorithm has proven to be effective in automatically computing the crack lengths and widths. Moreover, the implemented algorithm has the potential of replacing the manual crack detection method in Malawi.