Increasing world population and limited food resources, has made it inevitable to apply the benefits of modern technology to improve the efficiency of agricultural fields. Automatic plant type identification process is crucial not only to industries related to food production but also to environmentalists and related authorities. It increases productivity, contributes to a better understanding of the relationship between environmental factors and healthy crops. It is expected to reduce the labor costs for farmers and increase the operation speed and accuracy. In this paper, we propose a method to classify the type of plants in a video sequence. Our approach utilizes feature fusion together with color and texture features and support vector machine is used for classification. A variety of feature extraction techniques are employed in W-B, R-G and B-Y color spaces to extract color and textural features. Principal component analysis and t-distributed stochastic neighbor embedding methods are employed for dimension reduction. The performance of the approach is tested on dataset collected through a government supported project, TARBIL, for which over 1200 agro-stations are placed throughout Turkey. 5-fold cross validation technique as well as random test samples are used to test the accuracy of the system.