The SmaCS dataset is created to support research on object detection and scene understanding, specifically related to identifying the proper positioning of cabin luggage during taxi, take-off, and landing (TTL) operations. Examples of cabin luggage include backpacks, bottles, briefcases, camcorders, hats, laptops, shopping bags, suitcases, tote bags, etc. During TTL, these items should not be placed in areas that could compromise the safety, such as on seats, egresses, held by passengers, or in the aisle. On the other hand, other types of objects, such as magazines, books, food, smartphones, tablets, jackets, and wallets, do not have these restrictions and should be ignored. To collect the necessary data, a cabin mockup was built, and synthetic data was generated using 3D graphics. The mockup features one side of three cabin seat rows, an aisle, and an exterior made of polystyrene. The mockup was illuminated from three possible light sources: natural light from the room's windows, artificial light on the ceiling, and a spotlight beside the cabin window to mimic directional sunlight. The recordings were done on different days under varying lighting conditions. We utilized two cameras to observe two seat rows, one placed above the four seats closest to the window, and another above the aisle, to monitor the aisle and the two seats beside it. We established a recording protocol that 18 participants followed to simulate a variety of situations with cabin and non-cabin luggage objects. The protocol instructed passengers on actions such as how long to sit in a specific seat and where to place carried items. The goal of the protocol was to create a balanced number of scenarios, such as correctly and incorrectly placed luggage. Here, we make public the data of one of the seats (closest to the cabin window of the back row). For this seat, we obtained around 34K real and 7K synthetic samples.