YOLOv8-Peas: a lightweight drought tolerance method for peas based on seed germination vigor

Abstract

Introduction: Drought stress has become an important factor affecting global food production. Screening and breeding new varieties of peas (Pisum sativum L.) for drought-tolerant is of critical importance to ensure sustainable agricultural production and global food security. Germination rate and germination index are important indicators of seed germination vigor, and the level of germination vigor of pea seeds directly affects their yield and quality. The traditional manual germination detection can hardly meet the demand of full-time sequence nondestructive detection. We propose YOLOv8-Peas, an improved YOLOv8-n based method for the detection of pea germination vigor.

Methods: We constructed a pea germination dataset and used multiple data augmentation methods to improve the robustness of the model in real-world scenarios. By introducing the C2f-Ghost structure and depth-separable convolution, the model computational complexity is reduced and the model size is compressed. In addition, the original detector head is replaced by the self-designed PDetect detector head, which significantly improves the computational efficiency of the model. The Coordinate Attention (CA) mechanism is added to the backbone network to enhance the model's ability to localize and extract features from critical regions. The neck used a lightweight Content-Aware ReAssembly of FEatures (CARAFE) upsampling operator to capture and retain detailed features at low levels. The Adam optimizer is used to improve the model's learning ability in complex parameter spaces, thus improving the model's detection performance.

Results: The experimental results showed that the Params, FLOPs, and Weight Size of YOLOv8-Peas were 1.17M, 3.2G, and 2.7MB, respectively, which decreased by 61.2%, 61%, and 56.5% compared with the original YOLOv8-n. The mAP of YOLOv8-Peas was on par with that of YOLOv8-n, reaching 98.7%, and achieved a detection speed of 116.2FPS. We used PEG6000 to simulate different drought environments and YOLOv8-Peas to analyze and quantify the germination vigor of different genotypes of peas, and screened for the best drought-resistant pea varieties.

Discussion: Our model effectively reduces deployment costs, improves detection efficiency, and provides a scientific theoretical basis for drought-resistant genotype screening in pea.

Keywords: YOLOv8; drought tolerance; lightweight; pea seed; seed vitality.

Figure 1

Pea seed germination data acquisition equipment. (A) Physical image of the incubator. (B) Structure of the incubator. (C) Module training process. (D) Data acquisition system. (E) Edge computer. (F) LED fill light. (G) Data acquisition camera. (H) Schematic of the acquired images.

Figure 2

(A) Experimental flow chart. (B) Schematic of pea seed growth process.

Figure 3

Data augmentation process.

Figure 4

Schematic of not sprout and sprout pea seeds.

Figure 5

YOLOv8-Peas detector structure scheme. The k in the module represents the convolution kernel size, s represents the step size, and p represents the pooling kernel size.

Figure 6

Structure diagram of C2f_Ghost in YOLOv8-Peas. (A) C2f_Ghost module. (B) Ghost_Bottleneck module. (C) GhostConv module.

Figure 7

(A) Depthwise convolution schematic. (B) DBS module structure.

Figure 8

(A) Schematic of PCC module. (B) PDetect structure.

Figure 9

Structure of CA attention mechanism.

Figure 10

Schematic of the CARAFE upsampling operator.

Figure 11

Comparison of bilinear interpolation and CARAFE upsampling feature maps.

Figure 12

Multi-indicator normalized analysis.

Figure 13

Detection results of four lightweight algorithms for different growth conditions of peas. (A–E) Five different stages of pea germination.

Figure 14

(A) Schematic of the placement and growth process of different genotypes of peas. (B) Comparison of germination rate and germination index under two conditions. (C) Results of germination rate and germination index of four cultivars of peas under two conditions with time.