Robotic harvesting of cotton bolls will incorporate the benefits of manual picking as well as mechanical harvesting. For robotic harvesting, in-field cotton segmentation with minimal errors is desirable which is a cha...Robotic harvesting of cotton bolls will incorporate the benefits of manual picking as well as mechanical harvesting. For robotic harvesting, in-field cotton segmentation with minimal errors is desirable which is a challengingtask. In the present study, three lightweight fully convolutional neural network models were developed for thesemantic segmentation of in-field cotton bolls. Model 1 does not include any residual or skip connections,while model 2 consists of residual connections to tackle the vanishing gradient problem and skip connectionsfor feature concatenation. Model 3 along with residual and skip connections, consists of filters of multiplesizes. The effects of filter size and the dropout rate were studied. All proposed models segment the cotton bollssuccessfully with the cotton-IoU (intersection-over-union) value of above 88.0%. The highest cotton-IoU of91.03% was achieved by model 2. The proposed models achieved F1-score and pixel accuracy values greaterthan 95.0% and 98.0%, respectively. The developed models were compared with existing state-of-the-art networks namely VGG19, ResNet18, EfficientNet-B1, and InceptionV3. Despite having a limited number of trainableparameters, the proposed models achieved mean-IoU (mean intersection-over-union) of 93.84%, 94.15%, and94.65% against the mean-IoU values of 95.39%, 96.54%, 96.40%, and 96.37% obtained using state-of-the-art networks. The segmentation time for the developed models was reduced up to 52.0% compared to state-of-theart networks. The developed lightweight models segmented the in-field cotton bolls comparatively faster andwith greater accuracy. Hence, developed models can be deployed to cotton harvesting robots for real-time recognition of in-field cotton bolls for harvesting.展开更多
The agrochemical applicationwith conventional sprayers results inwastage of applied chemicals,which not only increases the economic losses but also pollutes the environment.In order to overcome these drawbacks,an imag...The agrochemical applicationwith conventional sprayers results inwastage of applied chemicals,which not only increases the economic losses but also pollutes the environment.In order to overcome these drawbacks,an image processing based real-time variable-rate chemical spraying systemwas developed for the precise application of agrochemicals in diseased paddy crop based on crop disease severity information.The developed system comprised ofweb cameras for image acquisition,laptop for image processing,microcontroller for controlling the system functioning,and solenoid valve assisted spraying nozzles.The chromatic aberration(CA)based image segmentation method was used to detect the diseased region of paddy plants.The system further calculated the disease severity level of paddy plants,based onwhich the solenoid valves remained on for a specific timeduration so that the required amount of agrochemical could be sprayed on the diseased paddy plants.Field performance of developed sprayer prototype was evaluated in the variable-rate application(VRA)and constant-rate application(CRA)modes.The field testing results showed a minimum 33.88%reduction in applied chemical while operating in the VRA mode as compared with the CRA mode.Hence,the developed systemappears promising and could be used extensively to reduce the cost of pest management as well as to control environmental pollution due to such agrochemicals.展开更多
文摘Robotic harvesting of cotton bolls will incorporate the benefits of manual picking as well as mechanical harvesting. For robotic harvesting, in-field cotton segmentation with minimal errors is desirable which is a challengingtask. In the present study, three lightweight fully convolutional neural network models were developed for thesemantic segmentation of in-field cotton bolls. Model 1 does not include any residual or skip connections,while model 2 consists of residual connections to tackle the vanishing gradient problem and skip connectionsfor feature concatenation. Model 3 along with residual and skip connections, consists of filters of multiplesizes. The effects of filter size and the dropout rate were studied. All proposed models segment the cotton bollssuccessfully with the cotton-IoU (intersection-over-union) value of above 88.0%. The highest cotton-IoU of91.03% was achieved by model 2. The proposed models achieved F1-score and pixel accuracy values greaterthan 95.0% and 98.0%, respectively. The developed models were compared with existing state-of-the-art networks namely VGG19, ResNet18, EfficientNet-B1, and InceptionV3. Despite having a limited number of trainableparameters, the proposed models achieved mean-IoU (mean intersection-over-union) of 93.84%, 94.15%, and94.65% against the mean-IoU values of 95.39%, 96.54%, 96.40%, and 96.37% obtained using state-of-the-art networks. The segmentation time for the developed models was reduced up to 52.0% compared to state-of-theart networks. The developed lightweight models segmented the in-field cotton bolls comparatively faster andwith greater accuracy. Hence, developed models can be deployed to cotton harvesting robots for real-time recognition of in-field cotton bolls for harvesting.
文摘The agrochemical applicationwith conventional sprayers results inwastage of applied chemicals,which not only increases the economic losses but also pollutes the environment.In order to overcome these drawbacks,an image processing based real-time variable-rate chemical spraying systemwas developed for the precise application of agrochemicals in diseased paddy crop based on crop disease severity information.The developed system comprised ofweb cameras for image acquisition,laptop for image processing,microcontroller for controlling the system functioning,and solenoid valve assisted spraying nozzles.The chromatic aberration(CA)based image segmentation method was used to detect the diseased region of paddy plants.The system further calculated the disease severity level of paddy plants,based onwhich the solenoid valves remained on for a specific timeduration so that the required amount of agrochemical could be sprayed on the diseased paddy plants.Field performance of developed sprayer prototype was evaluated in the variable-rate application(VRA)and constant-rate application(CRA)modes.The field testing results showed a minimum 33.88%reduction in applied chemical while operating in the VRA mode as compared with the CRA mode.Hence,the developed systemappears promising and could be used extensively to reduce the cost of pest management as well as to control environmental pollution due to such agrochemicals.
