Segmentation and recognition of filed sweet pepper based on improved self-attention convolutional neural networks

Abstract

Automatic and accurate recognition of the parts to be picked is the key to realize the intelligent picking of sweet pepper. However, pepper fruits are always covered by other organs, and small objects like stems and shoots are di cult to be recognized by machines or cameras under certain extreme conditions. To accurately segment and recognize all kinds of objects in sweet pepper images captured at night, three experiments were performed in this paper, and an enhanced model based on convolutional neural networks (CNNs) was eventually achieved. In experiment I, several semantic segmentation networks were trained on a small dataset, and the full-resolution residual network (FRRN) was taken as a primary network. Then, the impact of resolution of input images on the segmentation effect was investigated in experiment II. In order to strengthen the feature presentation of inconspicuous objects, the position attention module (PAM) was appended on top of the FRRN in experiment III.This architecture was further trained to provide more precise segmentation results. The experimental result shows that the mean intersection over union (IoU) is 78.88%, which is at least 1.94 percentage points higher than other models, and the mean pixel accuracy (PA) is 97.94% on the test set. The proposed method has higher generalization performance when facing unforeseen picking situations, meanwhile it is generic and can be applied to other fruits and vegetables.

Analysis of Fruit Images With Deep Learning: A Systematic Literature Review and Future Directions

“…The category "Other Fruits" corresponds to fruits that are analyzed in a single article, usually fruits of local origin. Agrivita 1 [115] Applied Intelligence 1 [116] Computational Intelligence and Neuroscience 1 [117] Computer Systems Science and Engineering 1 [118] Computers Electrical Engineering 1 [119] Data in Brief 1 [42] Ecological Informatics 1 [120] Electronics 1 [121] Energy Reports 1 [122] European Food Research and Technology 1 [123] Expert Systems With Applications 1 [124] Frontiers in Robotics and AI 1 [125] Horticulturae 1 [126] Journal of Robotics and Mechatronics 1 [135] Jurnal Kejuruteraan 1 [136] Mathematical Problems in Engineering 1 [137] Continued on next page Mechanical Systems and Signal Processing 1 [139] Multimedia Systems 1 [140] Neural Computing Applications 1 [141] Neural Network World 1 [142] Neural Networks 1 [143] Neurocomputing 1 [144] Plant and Cell Physiology 1 [145] Plants 1 [146] Postharvest Biology and Technology 1 [147] Procedia Computer Science 1 [148] Remote Sensing 1 [149] Results in Engineering 1 [150] Scientia Horticulturae 1 [151] Scientific African 1 [152] Scientific Programming 1 [153] Scientific Reports 1 [154] Sn Applied Sciences 1 [50] Sustainability 1 [155] Traitement du Signal 1 [156] Visual Computer 1 [52]…”