In order to solve the problems of high planting density, similar color, and serious occlusion between spikes in sorghum fields, such as difficult identification and detection of sorghum spikes, low accuracy and high false detection, and missed detection rates, this study proposes an improved sorghum spike detection method based on YOLOv8s. The method involves augmenting the information fusion capability of the YOLOv8 model’s neck module by integrating the Gold feature pyramid module. Additionally, the SPPF module is refined with the LSKA attention mechanism to heighten focus on critical features. To tackle class imbalance in sorghum detection and expedite model convergence, a loss function incorporating Focal-EIOU is employed. Consequently, the YOLOv8s-Gold-LSKA model, based on the Gold module and LSKA attention mechanism, is developed. Experimental results demonstrate that this improved method significantly enhances sorghum spike detection accuracy in natural field settings. The improved model achieved a precision of 90.72%, recall of 76.81%, mean average precision (mAP) of 85.86%, and an F1-score of 81.19%. Comparing the improved model of this study with the three target detection models of YOLOv5s, SSD, and YOLOv8, respectively, the improved model of this study has better detection performance. This advancement provides technical support for the rapid and accurate recognition of multiple sorghum spike targets in natural field backgrounds, thereby improving sorghum yield estimation accuracy. It also contributes to increased sorghum production and harvest, as well as the enhancement of intelligent harvesting equipment for agricultural machinery.

In the natural field environment, the high planting density of sorghum and severe occlusion among spikes substantially increases the difficulty of sorghum spike recognition, resulting in frequent false positives and false negatives. The target detection model suitable for this environment requires high computational power, and it is difficult to realize real-time detection of sorghum spikes on mobile devices. This study proposes a detection-tracking scheme based on improved YOLOv8s-GOLD-LSKA with optimized DeepSort, aiming to enhance yield estimation accuracy in complex agricultural field scenarios. By integrating the GOLD module’s dual-branch multi-scale feature fusion and the LSKA attention mechanism, a lightweight detection model is developed. The improved DeepSort algorithm enhances tracking robustness in occlusion scenarios by optimizing the confidence threshold filtering (0.46), frame-skipping count, and cascading matching strategy (n = 3, max_age = 40). Combined with the five-point sampling method, the average dry weight of sorghum spikes (0.12 kg) was used to enable rapid yield estimation. The results demonstrate that the improved model achieved a mAP of 85.86% (a 6.63% increase over the original YOLOv8), an F1 score of 81.19%, and a model size reduced to 7.48 MB, with a detection speed of 0.0168 s per frame. The optimized tracking system attained a MOTA of 67.96% and ran at 42 FPS. Image- and video-based yield estimation accuracies reached 89–96% and 75–93%, respectively, with single-frame latency as low as 0.047 s. By optimizing the full detection–tracking–yield pipeline, this solution overcomes challenges in small object missed detections, ID switches under occlusion, and real-time processing in complex scenarios. Its lightweight, high-efficiency design is well suited for deployment on UAVs and mobile terminals, providing robust technical support for intelligent sorghum monitoring and precision agriculture management, and thereby playing a crucial role in driving agricultural digital transformation.