As of today, sonar imaging is the most effective means of documenting the subsea environment. Existing sonar imaging systems generally rely on conventional beamforming methods to form the image. While conventional beamformers are robust and simple, they leave many of the challenges of sonar imaging unresolved. Sonar images are often degraded by noise, and the image resolution as well as the range at which useful images can be obtained is limited. This thesis addresses the use of adaptive beamforming and imaging methods applied to active sonar. The goal of an adaptive beamformer in this context is to improve the quality of the sonar image by allowing the beamformer to adapt to the situation, recognizing sources of noise and interference and suppressing them before they have the chance to contaminate the image. The desired result is an image containing more useful and correct information, less noise, and improved image resolution. Focus has been on investigating how different adaptive methods can be implemented in a practical setting, and analyzing the performance of each method. Key challenges that are addressed include coherent signals, arbitrary array geometries, computational load, and robustness. Two of the most common adaptive beamforming methods, the minimum variance distortionless response (MVDR) and the amplitude and phase estimation (APES) beamformers, are considered, as well as a low complexity variant of the adaptive MVDR beamformer. Adaptive imaging methods based on aperture coherence represent a promising class of adaptive methods, and are also considered. We conclude that in many cases, improved image quality is obtained by using adaptive beamforming methods.