Accurate information on crop distribution is of great importance for a range of applications including crop yield estimation, greenhouse gas emission measurement and management policy formulation. Fine spatial resolution (FSR) remotely sensed imagery provides new opportunities for crop mapping at a detailed level. However, crop classification from FSR imagery is known to be challenging due to the great intra-class variability and low inter-class disparity in the data.

Recently, Scientists from Northeast Institute of Geography and Agroecology of Chinese Academy of Sciences proposed a novel hybrid method (OSVM-OCNN) for crop classification from FSR imagery, which combines a shallow-structured object-based support vector machine (OSVM) with a deep-structured object-based convolutional neural network (OCNN).

Unlike pixel-wise classification methods, the OSVM-OCNN method operates on objects as the basic units of analysis and, thus, classifies remotely sensed images at the object level. The proposed OSVM-OCNN harvests the complementary characteristics of the two sub-models, the OSVM with effective extraction of low-level within-object features and the OCNN with capture and utilization of high-level between-object information. By using a rule-based fusion strategy based primarily on the OCNN’s prediction, the two sub-models were fused in a concise and effective manner.

Scientists investigated the effectiveness of the proposed method over two test sites that have distinctive and heterogeneous patterns of different crops in the Sacramento Valley, California, using FSR Synthetic Aperture Radar (SAR) and FSR multispectral data, respectively. Experimental results illustrated that the new proposed OSVM-OCNN approach increased markedly the classification accuracy for most of crop types over the two sites, and it consistently achieved the most accurate accuracy in comparison with its two object-based sub-models (OSVM and OCNN) as well as the pixel-wise SVM (PSVM) and CNN (PCNN) methods.

Overall, the presented OSVM-OCNN method is an effective and efficient approach for accurate crop classification (and classification of other complex landscapes) using FSR remotely sensed images, and it is suitable for different types of FSR remotely sensed images.

This study entitled " A hybrid OSVM-OCNN Method for Crop Classification from Fine Spatial Resolution Remotely Sensed Imagery " has been published online in Remote Sensing.

Contact:

LI Huapeng Ph.D. Associate Professor

Northeast Institute of Geography and Agroecology, CAS

Tel: 0431-85542230

E-mail:lihuapeng@iga.ac.cn