Abstract: Driverless cars in the complex environment of the open pit mining area encountered falling rocks, puddles, pedestrians and other obstacles have great safety hazards, easy to cause vehicle rollover, stuck in the car, resulting in the risk of loss of property or pose a threat to the safety of personnel, therefore, the complex and changing terrain environment on the road of the open pit mine as an important problem solving of the open pit mine unmanned vehicles in the mining intelligence, the need to measure the depth of obstacles in front of the car of the while guaranteeing the accuracy and speed of obstacle detection. The Feffol network model proposed in this paper selects Efficient-v2 as the backbone network structure for feature extraction in the feature extraction stage, selects the Ebifpn feature pyramid module based on the SppCSP structure with SppCSP structure to improve the feature sensing field while enhancing the feature information of different sizes, uses the Focal Loss and CIoU Loss loss functions to balance positive and negative samples, and solve the problem of method failure when there is no intersection between the prediction frame and the real detection frame. Aiming at the current stage of obstacle detection in open pit mines, most of which are in the two-dimensional stage, and can only recognize the target obstacles, but lack of measurement of the depth information of the obstacles, and can not make a correct decision on the obstacles in front of them; this paper is based on the binocular camera, and provides the support of the depth data of the obstacles in front of the unmanned vehicle by the method of binocular vision depth detection. The test results show that: Feffol's detection accuracy is 90.09%, detection speed is 9.75 it/s, compared with other mainstream type network, Feffol can further improve the monitoring accuracy at the same time, the monitoring speed can also meet the unmanned mining area unmanned mining road obstacle detection obstacle avoidance data decision-making needs, at the same time the depth of the obstacle in front of the vehicle to obtain, so that the image recognition Application in open pit mines is more feasible, providing an important basis for the safe traveling of unmanned vehicles in open pit mines.