This paper discusses vision-based static obstacle avoidance for nonholonomic robots. The robot is equipped with an inertial measurement unit that provides measurements of the vehicle's position and velocity, and a monocular camera that detects the obstacles. The obstacle avoidance algorithm deforms the vehicle's original path around isolated obstacles in a direction that minimizes a given potential function. This potential function is defined such that larger distances between the vehicle and obstacles yield lower values. Two estimation schemes are applied for the estimation task. The first is an existing method known in the literature as identifer-based observer that provides exponential convergence rate for the resulting error dynamics. The second is a recently-developed fast estimator that provides estimates of the unknown parameters with quantifiable bounds. It is shown that the performance of the fast estimator and its effect on the obstacle avoidance algorithm can be arbitrarily improved by appropriate choice of parameters as compared to the identifier-based observer method. Simulation results illustrate the theoretical findings.