Visual salient object detection (SOD) aims to discover eye-catching salient objects, while camouflaged object detection (COD) seeks to segment objects that are visually hidden in their surrounding environment. In this paper, considering the difficulty in defining salient and camouflaged properties of data when large-scale automated processing is launched, we propose a novel key object detection (KOD) task, which attempts to unify SOD and COD into one single task. This task treats both salient and camouflaged objects as key objects and aims to detect such key objects with salient and camouflaged properties. For KOD, we design a dual-branch network called DVNet, with a segmentation branch detecting key objects with salient and camouflaged properties in the scene, and additionally a judgment branch showcasing their saliency/camouflage degrees. Moreover, DVNet introduces a feature purification module (FPM) to focus more intently on mining features of key objects and employs a round-robin training strategy to enhance learning consistency. To demonstrate the effectiveness of DVNet for the KOD task, we construct a benchmark test set named KOD10K. We conduct extensive experiments on KOD10K and public SOD and COD datasets. DVNet achieves the best performance on KOD10K and also achieves decent performance on both SOD and COD datasets, demonstrating the significance of the proposed KOD task and the superiority of DVNet in detecting salient and camouflaged objects simultaneously.