Collision avoidance of drones in a complex environment, especially in an indoor environment, is a challenging task. This paperdevelops an obstacle avoidance system for small multi-rotor drones based on a deep reinforcement learning algorithm using only amonocular camera. The proposed method comprises two steps: depth estimation and navigation decision-making. For the depth estimationstep, a pre-trained depth estimation algorithm based on a CNN (Convolutional Neural Network) is used. In the navigation decision-makingstep, a dueling double deep Q-network is employed. The entire training procedure is performed in a Gazebo simulation environment usinga robot operating system. To validate the robustness of the proposed approach, various simulations and experiments are conducted using aParrot Bebop2 drone in an indoor corridor. We demonstrate that the proposed algorithm successfully navigates through a narrow corridorcomprising a texture-free wall, people, and boxes. A supplementary video clip of the experiments can be found at https://youtu.be/oSQHCsvuE-8.