Search

This paper proposes a novel technique for fruit detection in natural environments which is applicable in automatic harvesting robots, yield estimation systems and quality monitoring systems. As most color-based techniques are highly sensitive to illumination changes and low contrasts between fruits and leaves, the proposed technique, conversely, is based on contour information. Firstly, a discriminative shape descriptor is derived to represent geometrical properties of arbitrary fragment, and applied to a bidirectional partial shape matching to detect sub-fragments of interest that match parts of a reference contour. Then, a novel probabilistic Hough transform is developed to aggregate these sub-fragments for obtaining fruit candidates. Finally, all fruit candidates are verified by a support vector machine classifier trained on color and texture features. Citrus, tomato, pumpkin, bitter gourd, towel gourd and mango datasets were provided. Experiments on these datasets demonstrated that the proposed approach was competitive for detecting most type of fruits, such as green, orange, circular and non-circular, in natural environments. [ABSTRACT FROM AUTHOR]

A novel detection algorithm based on color, depth, and shape information is proposed for detecting spherical or cylindrical fruits on plants in natural environments and thus guiding harvesting robots to pick them automatically. A probabilistic image segmentation method is first presented to segment a red–green–blue image as a binary mask. Multiplied by this mask, a filtered depth image is obtained. Region growing, a region-based image segmentation method, is then applied to group the depth image into multiple clusters. Each cluster represents a fruit, leaf, or branch that is later transformed into a point cloud. Next, a 3D shape detection method based on M-estimator sample consensus, a model parameter estimator, is employed to detect potential fruits from each point cloud. Finally, an angle/color/shape-based global point cloud descriptor (GPCD) is developed to extract a feature vector for an entire point cloud, and a support vector machine classifier trained on the GPCD features is used to exclude false positives. Pepper, eggplant, and guava datasets were captured in the field. For the pepper, eggplant, and guava datasets, the detection precision was 0.864, 0.886, and 0.888, and the recall was 0.889, 0.762, and 0.812, respectively. Experiments revealed that the proposed algorithm was universal and robust and hence applicable to an agricultural harvesting robot. [ABSTRACT FROM AUTHOR]