The present study evaluates the speed and acceleration characteristics at the merging and diverging sections near two toll plazas located on National Highway under mixed traffic conditions using trajectory data obtained from video recorded using unmanned aerial vehicles (UAVs). The whole study section of 280 m is divided into zones of 20 m each, and the speed-distance and acceleration-distance relations are studied. The study analyzes the speed variations among vehicle classes in merging and diverging sections. The study shows that due to heterogeneous traffic and weak lane discipline, the speed distribution deviates from the normal distribution and follows the generalized extreme value (GEV) distribution in merging and diverging sections. The average maximum lateral speed is 3.0 km/h in the diverging section and 8.0 km/h in the diverging section (2.6 times higher than in the diverging section). The overall lane selection and lane changes are only prominent in the range from 40 m to 160 m in the merging section and the range from 100 m to 200 m in the diverging section. The results of acceleration modeling indicate that most vehicle classes follow a parabolic profile, except two-wheelers (2Ws) and light commercial vehicles (LCVs), whereas cars follow a dual-regime model in the diverging section, which is consistent with previous literature. The study also identified critical speeds for each vehicle class in both the merging and diverging sections, which can be useful in designing toll plaza facilities and informing safety measures.