Abstract
Recognition and localization of ripe strawberries is the basis of strawberry automatic picking system. Aiming at the problems of outdoor illumination change, uneven brightness, mutual occlusion of fruits and leaves, low recognition rate and poor generalization ability of traditional recognition methods, this paper proposes a mature strawberry target detection method based on improved single shot multibox detector (SSD) in-depth learning. The lightweight network MobileNet V2 was used as the basic network in SSD model to reduce the time spent in extracting image features and the amount of computation. The information loss caused by downsampling operation was avoided while synthesizing multi-scale features. The target of strawberry image recognition was established through the TensorFlow depth neural network framework. The results showed that the mAP of the model test set was 82.38%, the recognition accuracy of the improved SSD model was 97.4%, the recall rate was 94.5%, and the average recognition time of single frame image was 125 ms. This method can effectively recognize mature strawberries in natural environment and provide technical support for automatic production of strawberry harvesting.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Qiu, Q., He, C.: Design of strawberry picking car based on TCS3200 color recognition. Mech. Res. Appl. 32(3), 104–106 (2019)
Gongal, A., Amatya, S., Karkee, M., et al.: Sensors and systems for fruit detection and localization: a review. Comput. Electron. Agric. 116, 8–19 (2015)
Lu, J., Sang, N.: Detecting citrus fruits and occlusion recovery under natural illumination conditions. Comput. Electron. Agric. 110, 121–130 (2015)
Arefi, A., Motlagh, A., Mollazade, K., et al.: Recognition and localization of ripen tomato based on machine vision. Aust. J. Crop Sci. 5(10), 1144 (2011)
Zhou, R., Damerow, L., Sun, Y., et al.: Using colour features of cv. ‘Gala’ apple fruits in an orchard in image processing to predict yield. Precis. Agric. 13(5), 568–580 (2012)
Wachs, J., Stern, H., Burks, T., et al.: Low and high-level visual feature-based apple detection from multi-modal images. Precis. Agric. 11(6), 717–735 (2010)
Zhu, A., Yang, L.: An improved FCM algorithm for ripe fruit image segmentation. In: IEEE International Conference on Information and Automation, pp. 436–441. IEEE (2014)
Linker, R., Cohen, O., Naor, A.: Determination of the number of green apples in RGB images recorded in orchards. Comput. Electron. Agric. 81(1), 45–57 (2012)
Arefi, A., Motlagh, M.: Development of an expert system based on wavelet transform and artificial neural networks for the ripe tomato harvesting robot. Aust. J. Crop Sci. 7(5), 699–705 (2013)
Qiang, L., Jianrong, C., Bin, L., et al.: Identification of fruit and branch in natural scenes for citrus harvesting robot using machine vision and support vector machine. Int. J. Agric. Biol. Eng. 7(2), 115–121 (2014)
Zhao, Y., Lee, W., He, D.: Immature green citrus detection based on colour feature and sum of absolute transformed difference (SATD) using colour images in the citrus grove. Comput. Electron. Agric. 124, 243–253 (2016)
Hu, Q., Wang, P., Shen, C., et al.: Pushing the limits of deep CNNs for pedestrian detection. IEEE Trans. Circ. Syst. Video Technol. 28(6), 1358–1368 (2017)
Girshick, R., Donahue, J., Darrell, T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of 29th Annual Conference on Neural Information Processing Systems (2015)
Xiong, J., Liu, Z., Lin, R., et al.: Unmanned aerial vehicle vision detection technology of green mango on tree in natural environment. Trans. Chin. Soc. Agric. Mach. 49(11), 23–29 (2018)
Xue, Y., Huang, N., Tu, S., et al.: Immature mango detection based on improved YOLOv2. Trans. CSAE. 34(7), 173–179 (2018)
Zhao, D., Liu, X., Sun, Y., et al.: Detection of underwater crabs based on machine vision. Trans. Chin. Soc. Agric. Mach. 50(3), 151–158 (2019)
Zhao, K., He, D.: Recognition of individual dairy cattle based on convolutional neural networks. Trans. CSAE 31(5), 181–187 (2015)
Yang, Q., Xiao, D., Lin, S.: Feeding behavior recognition for group-housed pigs with the faster R-CNN. Comput. Electron. Agric. 155, 453–460 (2018)
Acknowledegments
This work is supported by the National Natural Science Foundation of China No. 61504072.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, Z., Xiao, D. (2020). Recognition Method of Mature Strawberry Based on Improved SSD Deep Convolution Neural Network. In: Pan, L., Liang, J., Qu, B. (eds) Bio-inspired Computing: Theories and Applications. BIC-TA 2019. Communications in Computer and Information Science, vol 1160. Springer, Singapore. https://doi.org/10.1007/978-981-15-3415-7_22
Download citation
DOI: https://doi.org/10.1007/978-981-15-3415-7_22
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3414-0
Online ISBN: 978-981-15-3415-7
eBook Packages: Computer ScienceComputer Science (R0)