This paper proposes a novel concept for the image based visual control, which is called the goal-oriented just-intime visual servoing. We apply this control to ball catching task by a robot arm. This approach contains the processes: 1. To achieve the control of robot arm 3D motion using visual observation, we employ no information to reconstruct 3D space from the 2D images, and only define the goal of the task in the image planes. 2. Then we apply the control to achieve all the 2D defined tasks simultaneously. 3. If all the respective goal defined in images are accomplished simultaneously, the 3D task can be interpreted to be achieved. Further more, in the proposed method, we estimate the Jacobian on-line to combine the image motion and 3D motion of the robot arm without the prior knowledge of the arm and camera structures for hand-eye and camera calibrations. The actual experiments show the feasibility of the proposed method for visual control of the ball catching robot.