The Bactrocera oleae has been a major pest of the olive, affecting the quality of the cultivated crop and the livelihood of the farmers relying on it since ancient times. We propose an intelligent, autonomous, remotely accessible B. oleae trap utilising a chromotropic, adhesive film for insect capturing, as well as sensors for the collection of microclimatic environmental data. By making use of image recognition techniques and machine learning the system will provide real-time information as well as predictions with regard to B. oleae population development, enabling a faster, more accurate response to potential or emerging threats. We seek to improve the effectiveness of pest monitoring by enabling higher automation in monitoring and decision making, optimising response times, lowering labour and material costs, as well as reducing the environmental impact of chemical use in pest control. Furthermore, we wish to achieve integration into a unified Ambient Intelligence platform, providing easy system access via different interfaces to a variety of potentially relevant stakeholders, from the relative novice to the expert. While still at the prototype phase, initial tests appear to be encouraging, with the system operating within the initially expected parameters. Upon successful completion, it is envisioned that the effectiveness of the system can be evaluated in direct comparison to traditional methods through the lengthier deployment of several traps, before potential further expansion.