Object detection and recognition is a subfield of computer vision that is currently heavily based on machine learning. For the past decade, the field of machine learning has been dominated by so-called “deep neural networks”, which takes advantage of the improvements in computing power and data availability. A In the proposed method a convolutional autoencoder-decoder network for the semantic segmentation of the input image into predefined objects is presented. The proposed algorithm in the section of encoder uses the max pooling layer index in encoder part in order to produce a feature map. Then in the next block, the proposed network segments the input image into recognized objects. Finally, in order to evaluate the proposed method, the proposed algorithm is applied to Cam-Vid dataset. Experimental results show that the proposed method obtains mean intersection over union on segmentation area of 62.3%, which shows the superiority of the proposed method in comparison with other similar methods. Keywords: convolutional Neural Network, Deep Learning, semantic sImage egmentation, Object Detection
